clinno commited on
Commit
e95fd93
1 Parent(s): e32df28

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ base_model: NousResearch/Meta-Llama-3-8B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - full
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: sft
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # sft
18
+
19
+ This model is a fine-tuned version of [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct) on the identity and the iplaw20240808 datasets.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 1.0843
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 1e-05
41
+ - train_batch_size: 1
42
+ - eval_batch_size: 1
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 8
45
+ - total_train_batch_size: 8
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: cosine
48
+ - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 9.0
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss |
54
+ |:-------------:|:------:|:----:|:---------------:|
55
+ | 1.3784 | 0.8469 | 500 | 1.4012 |
56
+ | 1.1764 | 1.6938 | 1000 | 1.2227 |
57
+ | 0.9808 | 2.5408 | 1500 | 1.1500 |
58
+ | 0.9778 | 3.3877 | 2000 | 1.1205 |
59
+ | 0.8815 | 4.2346 | 2500 | 1.0940 |
60
+ | 0.8159 | 5.0815 | 3000 | 1.0748 |
61
+ | 0.8317 | 5.9284 | 3500 | 1.0829 |
62
+ | 0.7269 | 6.7754 | 4000 | 1.0812 |
63
+ | 0.7372 | 7.6223 | 4500 | 1.0817 |
64
+ | 0.7366 | 8.4692 | 5000 | 1.0842 |
65
+
66
+
67
+ ### Framework versions
68
+
69
+ - Transformers 4.44.2
70
+ - Pytorch 2.4.1+cu121
71
+ - Datasets 2.21.0
72
+ - Tokenizers 0.19.1
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 8.994283294516197,
3
+ "eval_loss": 1.0843082666397095,
4
+ "eval_runtime": 21.0991,
5
+ "eval_samples_per_second": 24.883,
6
+ "eval_steps_per_second": 24.883,
7
+ "total_flos": 5.095460800932741e+17,
8
+ "train_loss": 0.9683849982173653,
9
+ "train_runtime": 5676.759,
10
+ "train_samples_per_second": 7.488,
11
+ "train_steps_per_second": 0.935
12
+ }
checkpoint-5310/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "NousResearch/Meta-Llama-3-8B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128009,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 8,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 500000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.44.2",
27
+ "use_cache": false,
28
+ "vocab_size": 128256
29
+ }
checkpoint-5310/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128009
7
+ ],
8
+ "max_length": 4096,
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.44.2"
12
+ }
checkpoint-5310/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e2b3bba182357967751ba25b34ef5149858fc5321b1a326066589aed1a3a882
3
+ size 4976698672
checkpoint-5310/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe8e803e15da12b9b2227fcd2e14ebdf6b5cfe3fcc8c947863eaef8c200a2d7c
3
+ size 4999802720
checkpoint-5310/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eb88d196a15aac180b8437683b358ebd28ef8599ce887f8960f54e6defb21f3
3
+ size 4915916176
checkpoint-5310/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f41e6f9a7ea6b66c8f678e4c03f5b1f9a9ca942bd3041d8d72e17f459665b495
3
+ size 1168138808
checkpoint-5310/model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16060522496
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
296
+ "model.norm.weight": "model-00004-of-00004.safetensors"
297
+ }
298
+ }
checkpoint-5310/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f6ecbd1a7b1fb45727950990be60443ee103a9984adf2151163c03d518e0fc0
3
+ size 1744904195
checkpoint-5310/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d10ad6c90de119ae0a3eeecda7366634ce107ef267b5fdd3ddd046f0a5ae742
3
+ size 14244
checkpoint-5310/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f43ebba2ec24259f4d03b694c184ff7a2e37aaf50a3da18fe55270b1fc641b5
3
+ size 1064
checkpoint-5310/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
checkpoint-5310/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-5310/tokenizer_config.json ADDED
@@ -0,0 +1,2065 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "padding_side": "right",
2063
+ "split_special_tokens": false,
2064
+ "tokenizer_class": "PreTrainedTokenizerFast"
2065
+ }
checkpoint-5310/trainer_state.json ADDED
@@ -0,0 +1,3830 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 8.994283294516197,
5
+ "eval_steps": 500,
6
+ "global_step": 5310,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01693838661867457,
13
+ "grad_norm": 5.0625,
14
+ "learning_rate": 1.8832391713747647e-07,
15
+ "loss": 2.0482,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.03387677323734914,
20
+ "grad_norm": 5.59375,
21
+ "learning_rate": 3.7664783427495294e-07,
22
+ "loss": 2.069,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.050815159856023716,
27
+ "grad_norm": 5.96875,
28
+ "learning_rate": 5.649717514124295e-07,
29
+ "loss": 2.0861,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.06775354647469828,
34
+ "grad_norm": 5.65625,
35
+ "learning_rate": 7.532956685499059e-07,
36
+ "loss": 2.0413,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.08469193309337286,
41
+ "grad_norm": 16.125,
42
+ "learning_rate": 9.416195856873824e-07,
43
+ "loss": 2.0095,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.10163031971204743,
48
+ "grad_norm": 17.75,
49
+ "learning_rate": 1.129943502824859e-06,
50
+ "loss": 2.0333,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.118568706330722,
55
+ "grad_norm": 14.3125,
56
+ "learning_rate": 1.3182674199623351e-06,
57
+ "loss": 2.0062,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.13550709294939656,
62
+ "grad_norm": 15.5625,
63
+ "learning_rate": 1.5065913370998117e-06,
64
+ "loss": 1.9655,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.15244547956807114,
69
+ "grad_norm": 14.4375,
70
+ "learning_rate": 1.6949152542372882e-06,
71
+ "loss": 1.9698,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.16938386618674572,
76
+ "grad_norm": 3.4375,
77
+ "learning_rate": 1.8832391713747648e-06,
78
+ "loss": 1.9211,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.18632225280542028,
83
+ "grad_norm": 2.703125,
84
+ "learning_rate": 2.071563088512241e-06,
85
+ "loss": 1.9071,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.20326063942409486,
90
+ "grad_norm": 3.453125,
91
+ "learning_rate": 2.259887005649718e-06,
92
+ "loss": 1.8766,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.22019902604276942,
97
+ "grad_norm": 2.9375,
98
+ "learning_rate": 2.448210922787194e-06,
99
+ "loss": 1.8211,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.237137412661444,
104
+ "grad_norm": 3.859375,
105
+ "learning_rate": 2.6365348399246702e-06,
106
+ "loss": 1.7678,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.2540757992801186,
111
+ "grad_norm": 2.515625,
112
+ "learning_rate": 2.8248587570621473e-06,
113
+ "loss": 1.6984,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.2710141858987931,
118
+ "grad_norm": 2.671875,
119
+ "learning_rate": 3.0131826741996235e-06,
120
+ "loss": 1.6916,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.2879525725174677,
125
+ "grad_norm": 2.515625,
126
+ "learning_rate": 3.2015065913371e-06,
127
+ "loss": 1.7083,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.3048909591361423,
132
+ "grad_norm": 2.609375,
133
+ "learning_rate": 3.3898305084745763e-06,
134
+ "loss": 1.7021,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.32182934575481686,
139
+ "grad_norm": 3.109375,
140
+ "learning_rate": 3.5781544256120534e-06,
141
+ "loss": 1.654,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.33876773237349145,
146
+ "grad_norm": 1.875,
147
+ "learning_rate": 3.7664783427495296e-06,
148
+ "loss": 1.6125,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.355706118992166,
153
+ "grad_norm": 1.9765625,
154
+ "learning_rate": 3.954802259887006e-06,
155
+ "loss": 1.6243,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.37264450561084056,
160
+ "grad_norm": 2.046875,
161
+ "learning_rate": 4.143126177024482e-06,
162
+ "loss": 1.6311,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.38958289222951514,
167
+ "grad_norm": 2.375,
168
+ "learning_rate": 4.331450094161959e-06,
169
+ "loss": 1.6088,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.4065212788481897,
174
+ "grad_norm": 1.9765625,
175
+ "learning_rate": 4.519774011299436e-06,
176
+ "loss": 1.6126,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.42345966546686425,
181
+ "grad_norm": 2.0,
182
+ "learning_rate": 4.7080979284369114e-06,
183
+ "loss": 1.5862,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.44039805208553884,
188
+ "grad_norm": 1.9296875,
189
+ "learning_rate": 4.896421845574388e-06,
190
+ "loss": 1.5869,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.4573364387042134,
195
+ "grad_norm": 2.03125,
196
+ "learning_rate": 5.084745762711865e-06,
197
+ "loss": 1.568,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.474274825322888,
202
+ "grad_norm": 2.234375,
203
+ "learning_rate": 5.2730696798493405e-06,
204
+ "loss": 1.4917,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.4912132119415626,
209
+ "grad_norm": 3.0,
210
+ "learning_rate": 5.461393596986818e-06,
211
+ "loss": 1.5614,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.5081515985602372,
216
+ "grad_norm": 2.09375,
217
+ "learning_rate": 5.6497175141242946e-06,
218
+ "loss": 1.5684,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.5250899851789117,
223
+ "grad_norm": 1.765625,
224
+ "learning_rate": 5.83804143126177e-06,
225
+ "loss": 1.5933,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.5420283717975862,
230
+ "grad_norm": 1.953125,
231
+ "learning_rate": 6.026365348399247e-06,
232
+ "loss": 1.5864,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.5589667584162609,
237
+ "grad_norm": 1.9296875,
238
+ "learning_rate": 6.2146892655367244e-06,
239
+ "loss": 1.539,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.5759051450349354,
244
+ "grad_norm": 2.125,
245
+ "learning_rate": 6.4030131826742e-06,
246
+ "loss": 1.4972,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.59284353165361,
251
+ "grad_norm": 1.765625,
252
+ "learning_rate": 6.591337099811677e-06,
253
+ "loss": 1.5136,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.6097819182722846,
258
+ "grad_norm": 1.921875,
259
+ "learning_rate": 6.779661016949153e-06,
260
+ "loss": 1.5159,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.6267203048909591,
265
+ "grad_norm": 1.8125,
266
+ "learning_rate": 6.96798493408663e-06,
267
+ "loss": 1.4829,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.6436586915096337,
272
+ "grad_norm": 1.9296875,
273
+ "learning_rate": 7.156308851224107e-06,
274
+ "loss": 1.4972,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.6605970781283083,
279
+ "grad_norm": 2.140625,
280
+ "learning_rate": 7.3446327683615825e-06,
281
+ "loss": 1.4115,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.6775354647469829,
286
+ "grad_norm": 2.296875,
287
+ "learning_rate": 7.532956685499059e-06,
288
+ "loss": 1.5167,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.6944738513656574,
293
+ "grad_norm": 1.96875,
294
+ "learning_rate": 7.721280602636536e-06,
295
+ "loss": 1.4496,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.711412237984332,
300
+ "grad_norm": 1.7734375,
301
+ "learning_rate": 7.909604519774012e-06,
302
+ "loss": 1.4258,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.7283506246030066,
307
+ "grad_norm": 3.28125,
308
+ "learning_rate": 8.097928436911489e-06,
309
+ "loss": 1.498,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.7452890112216811,
314
+ "grad_norm": 2.078125,
315
+ "learning_rate": 8.286252354048965e-06,
316
+ "loss": 1.4588,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.7622273978403558,
321
+ "grad_norm": 2.03125,
322
+ "learning_rate": 8.47457627118644e-06,
323
+ "loss": 1.4085,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.7791657844590303,
328
+ "grad_norm": 1.9765625,
329
+ "learning_rate": 8.662900188323918e-06,
330
+ "loss": 1.4479,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.7961041710777048,
335
+ "grad_norm": 2.25,
336
+ "learning_rate": 8.851224105461394e-06,
337
+ "loss": 1.4711,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.8130425576963795,
342
+ "grad_norm": 2.078125,
343
+ "learning_rate": 9.039548022598871e-06,
344
+ "loss": 1.4004,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.829980944315054,
349
+ "grad_norm": 2.09375,
350
+ "learning_rate": 9.227871939736347e-06,
351
+ "loss": 1.3785,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.8469193309337285,
356
+ "grad_norm": 1.765625,
357
+ "learning_rate": 9.416195856873823e-06,
358
+ "loss": 1.3784,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.8469193309337285,
363
+ "eval_loss": 1.401244044303894,
364
+ "eval_runtime": 21.2893,
365
+ "eval_samples_per_second": 24.66,
366
+ "eval_steps_per_second": 24.66,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 0.8638577175524031,
371
+ "grad_norm": 1.96875,
372
+ "learning_rate": 9.6045197740113e-06,
373
+ "loss": 1.4401,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 0.8807961041710777,
378
+ "grad_norm": 1.6640625,
379
+ "learning_rate": 9.792843691148776e-06,
380
+ "loss": 1.4191,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 0.8977344907897523,
385
+ "grad_norm": 1.6015625,
386
+ "learning_rate": 9.981167608286254e-06,
387
+ "loss": 1.3972,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 0.9146728774084268,
392
+ "grad_norm": 1.7421875,
393
+ "learning_rate": 9.999912491660088e-06,
394
+ "loss": 1.4051,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 0.9316112640271014,
399
+ "grad_norm": 1.8984375,
400
+ "learning_rate": 9.999609997627497e-06,
401
+ "loss": 1.3855,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 0.948549650645776,
406
+ "grad_norm": 1.765625,
407
+ "learning_rate": 9.999091450621204e-06,
408
+ "loss": 1.4033,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 0.9654880372644505,
413
+ "grad_norm": 1.640625,
414
+ "learning_rate": 9.99835687304968e-06,
415
+ "loss": 1.4429,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 0.9824264238831252,
420
+ "grad_norm": 1.8515625,
421
+ "learning_rate": 9.997406296656937e-06,
422
+ "loss": 1.3925,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 0.9993648105017997,
427
+ "grad_norm": 1.78125,
428
+ "learning_rate": 9.996239762521152e-06,
429
+ "loss": 1.4055,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.0163031971204743,
434
+ "grad_norm": 2.203125,
435
+ "learning_rate": 9.994857321052887e-06,
436
+ "loss": 1.2929,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.0332415837391489,
441
+ "grad_norm": 1.8203125,
442
+ "learning_rate": 9.993259031992921e-06,
443
+ "loss": 1.2752,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.0501799703578234,
448
+ "grad_norm": 1.59375,
449
+ "learning_rate": 9.991444964409665e-06,
450
+ "loss": 1.3491,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.067118356976498,
455
+ "grad_norm": 1.8515625,
456
+ "learning_rate": 9.989415196696169e-06,
457
+ "loss": 1.3204,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.0840567435951725,
462
+ "grad_norm": 1.625,
463
+ "learning_rate": 9.98716981656675e-06,
464
+ "loss": 1.3425,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.1009951302138472,
469
+ "grad_norm": 1.921875,
470
+ "learning_rate": 9.98470892105318e-06,
471
+ "loss": 1.3116,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.1179335168325217,
476
+ "grad_norm": 1.8203125,
477
+ "learning_rate": 9.982032616500516e-06,
478
+ "loss": 1.307,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.1348719034511963,
483
+ "grad_norm": 1.875,
484
+ "learning_rate": 9.979141018562494e-06,
485
+ "loss": 1.3132,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.1518102900698708,
490
+ "grad_norm": 1.84375,
491
+ "learning_rate": 9.976034252196524e-06,
492
+ "loss": 1.3304,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.1687486766885455,
497
+ "grad_norm": 1.6796875,
498
+ "learning_rate": 9.9727124516583e-06,
499
+ "loss": 1.347,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.18568706330722,
504
+ "grad_norm": 1.734375,
505
+ "learning_rate": 9.969175760495997e-06,
506
+ "loss": 1.2844,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.2026254499258946,
511
+ "grad_norm": 1.6953125,
512
+ "learning_rate": 9.965424331544064e-06,
513
+ "loss": 1.2891,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.2195638365445691,
518
+ "grad_norm": 1.828125,
519
+ "learning_rate": 9.961458326916624e-06,
520
+ "loss": 1.3258,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.2365022231632437,
525
+ "grad_norm": 1.609375,
526
+ "learning_rate": 9.95727791800046e-06,
527
+ "loss": 1.2944,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.2534406097819182,
532
+ "grad_norm": 1.6171875,
533
+ "learning_rate": 9.952883285447622e-06,
534
+ "loss": 1.2602,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.2703789964005927,
539
+ "grad_norm": 1.796875,
540
+ "learning_rate": 9.948274619167608e-06,
541
+ "loss": 1.2353,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.2873173830192675,
546
+ "grad_norm": 1.6953125,
547
+ "learning_rate": 9.943452118319165e-06,
548
+ "loss": 1.2749,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.304255769637942,
553
+ "grad_norm": 1.765625,
554
+ "learning_rate": 9.938415991301675e-06,
555
+ "loss": 1.2432,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.3211941562566165,
560
+ "grad_norm": 1.625,
561
+ "learning_rate": 9.933166455746159e-06,
562
+ "loss": 1.2824,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.3381325428752913,
567
+ "grad_norm": 1.5703125,
568
+ "learning_rate": 9.927703738505863e-06,
569
+ "loss": 1.2335,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.3550709294939658,
574
+ "grad_norm": 1.5625,
575
+ "learning_rate": 9.922028075646465e-06,
576
+ "loss": 1.3065,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.3720093161126403,
581
+ "grad_norm": 1.5703125,
582
+ "learning_rate": 9.91613971243586e-06,
583
+ "loss": 1.2443,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.3889477027313148,
588
+ "grad_norm": 1.578125,
589
+ "learning_rate": 9.910038903333574e-06,
590
+ "loss": 1.2303,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.4058860893499894,
595
+ "grad_norm": 1.90625,
596
+ "learning_rate": 9.90372591197976e-06,
597
+ "loss": 1.1844,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.422824475968664,
602
+ "grad_norm": 1.53125,
603
+ "learning_rate": 9.89720101118381e-06,
604
+ "loss": 1.2035,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.4397628625873384,
609
+ "grad_norm": 1.421875,
610
+ "learning_rate": 9.890464482912561e-06,
611
+ "loss": 1.2399,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.4567012492060132,
616
+ "grad_norm": 1.578125,
617
+ "learning_rate": 9.88351661827811e-06,
618
+ "loss": 1.227,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.4736396358246877,
623
+ "grad_norm": 1.484375,
624
+ "learning_rate": 9.876357717525245e-06,
625
+ "loss": 1.2589,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.4905780224433622,
630
+ "grad_norm": 1.84375,
631
+ "learning_rate": 9.86898809001845e-06,
632
+ "loss": 1.1935,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.507516409062037,
637
+ "grad_norm": 1.5,
638
+ "learning_rate": 9.861408054228556e-06,
639
+ "loss": 1.2177,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 1.5244547956807115,
644
+ "grad_norm": 1.3828125,
645
+ "learning_rate": 9.853617937718966e-06,
646
+ "loss": 1.2285,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 1.541393182299386,
651
+ "grad_norm": 1.3515625,
652
+ "learning_rate": 9.845618077131508e-06,
653
+ "loss": 1.226,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 1.5583315689180606,
658
+ "grad_norm": 1.421875,
659
+ "learning_rate": 9.837408818171884e-06,
660
+ "loss": 1.2536,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 1.575269955536735,
665
+ "grad_norm": 1.2578125,
666
+ "learning_rate": 9.82899051559472e-06,
667
+ "loss": 1.2041,
668
+ "step": 930
669
+ },
670
+ {
671
+ "epoch": 1.5922083421554096,
672
+ "grad_norm": 1.515625,
673
+ "learning_rate": 9.820363533188257e-06,
674
+ "loss": 1.2279,
675
+ "step": 940
676
+ },
677
+ {
678
+ "epoch": 1.6091467287740842,
679
+ "grad_norm": 1.2421875,
680
+ "learning_rate": 9.811528243758612e-06,
681
+ "loss": 1.1829,
682
+ "step": 950
683
+ },
684
+ {
685
+ "epoch": 1.6260851153927587,
686
+ "grad_norm": 1.6015625,
687
+ "learning_rate": 9.802485029113682e-06,
688
+ "loss": 1.1698,
689
+ "step": 960
690
+ },
691
+ {
692
+ "epoch": 1.6430235020114334,
693
+ "grad_norm": 1.234375,
694
+ "learning_rate": 9.793234280046627e-06,
695
+ "loss": 1.2212,
696
+ "step": 970
697
+ },
698
+ {
699
+ "epoch": 1.659961888630108,
700
+ "grad_norm": 1.234375,
701
+ "learning_rate": 9.783776396318998e-06,
702
+ "loss": 1.1377,
703
+ "step": 980
704
+ },
705
+ {
706
+ "epoch": 1.6769002752487827,
707
+ "grad_norm": 1.3203125,
708
+ "learning_rate": 9.77411178664346e-06,
709
+ "loss": 1.2086,
710
+ "step": 990
711
+ },
712
+ {
713
+ "epoch": 1.6938386618674572,
714
+ "grad_norm": 1.3125,
715
+ "learning_rate": 9.76424086866612e-06,
716
+ "loss": 1.1764,
717
+ "step": 1000
718
+ },
719
+ {
720
+ "epoch": 1.6938386618674572,
721
+ "eval_loss": 1.2227357625961304,
722
+ "eval_runtime": 20.8763,
723
+ "eval_samples_per_second": 25.148,
724
+ "eval_steps_per_second": 25.148,
725
+ "step": 1000
726
+ },
727
+ {
728
+ "epoch": 1.7107770484861318,
729
+ "grad_norm": 1.2421875,
730
+ "learning_rate": 9.754164068948482e-06,
731
+ "loss": 1.1537,
732
+ "step": 1010
733
+ },
734
+ {
735
+ "epoch": 1.7277154351048063,
736
+ "grad_norm": 1.453125,
737
+ "learning_rate": 9.743881822949025e-06,
738
+ "loss": 1.2405,
739
+ "step": 1020
740
+ },
741
+ {
742
+ "epoch": 1.7446538217234808,
743
+ "grad_norm": 1.1875,
744
+ "learning_rate": 9.733394575004373e-06,
745
+ "loss": 1.2403,
746
+ "step": 1030
747
+ },
748
+ {
749
+ "epoch": 1.7615922083421554,
750
+ "grad_norm": 1.40625,
751
+ "learning_rate": 9.722702778310096e-06,
752
+ "loss": 1.152,
753
+ "step": 1040
754
+ },
755
+ {
756
+ "epoch": 1.7785305949608299,
757
+ "grad_norm": 1.265625,
758
+ "learning_rate": 9.711806894901124e-06,
759
+ "loss": 1.1596,
760
+ "step": 1050
761
+ },
762
+ {
763
+ "epoch": 1.7954689815795044,
764
+ "grad_norm": 1.25,
765
+ "learning_rate": 9.700707395631787e-06,
766
+ "loss": 1.1555,
767
+ "step": 1060
768
+ },
769
+ {
770
+ "epoch": 1.8124073681981792,
771
+ "grad_norm": 1.171875,
772
+ "learning_rate": 9.689404760155465e-06,
773
+ "loss": 1.1611,
774
+ "step": 1070
775
+ },
776
+ {
777
+ "epoch": 1.8293457548168537,
778
+ "grad_norm": 1.640625,
779
+ "learning_rate": 9.677899476903857e-06,
780
+ "loss": 1.1727,
781
+ "step": 1080
782
+ },
783
+ {
784
+ "epoch": 1.8462841414355282,
785
+ "grad_norm": 1.2265625,
786
+ "learning_rate": 9.666192043065875e-06,
787
+ "loss": 1.1526,
788
+ "step": 1090
789
+ },
790
+ {
791
+ "epoch": 1.863222528054203,
792
+ "grad_norm": 1.265625,
793
+ "learning_rate": 9.654282964566159e-06,
794
+ "loss": 1.1677,
795
+ "step": 1100
796
+ },
797
+ {
798
+ "epoch": 1.8801609146728775,
799
+ "grad_norm": 1.1953125,
800
+ "learning_rate": 9.642172756043217e-06,
801
+ "loss": 1.1363,
802
+ "step": 1110
803
+ },
804
+ {
805
+ "epoch": 1.897099301291552,
806
+ "grad_norm": 1.1953125,
807
+ "learning_rate": 9.629861940827181e-06,
808
+ "loss": 1.1216,
809
+ "step": 1120
810
+ },
811
+ {
812
+ "epoch": 1.9140376879102265,
813
+ "grad_norm": 1.2109375,
814
+ "learning_rate": 9.617351050917197e-06,
815
+ "loss": 1.1432,
816
+ "step": 1130
817
+ },
818
+ {
819
+ "epoch": 1.930976074528901,
820
+ "grad_norm": 1.0859375,
821
+ "learning_rate": 9.604640626958428e-06,
822
+ "loss": 1.1714,
823
+ "step": 1140
824
+ },
825
+ {
826
+ "epoch": 1.9479144611475756,
827
+ "grad_norm": 1.21875,
828
+ "learning_rate": 9.591731218218694e-06,
829
+ "loss": 1.1999,
830
+ "step": 1150
831
+ },
832
+ {
833
+ "epoch": 1.9648528477662501,
834
+ "grad_norm": 1.078125,
835
+ "learning_rate": 9.57862338256474e-06,
836
+ "loss": 1.1692,
837
+ "step": 1160
838
+ },
839
+ {
840
+ "epoch": 1.9817912343849249,
841
+ "grad_norm": 1.125,
842
+ "learning_rate": 9.565317686438122e-06,
843
+ "loss": 1.1193,
844
+ "step": 1170
845
+ },
846
+ {
847
+ "epoch": 1.9987296210035994,
848
+ "grad_norm": 0.92578125,
849
+ "learning_rate": 9.551814704830734e-06,
850
+ "loss": 1.1596,
851
+ "step": 1180
852
+ },
853
+ {
854
+ "epoch": 2.015668007622274,
855
+ "grad_norm": 0.96875,
856
+ "learning_rate": 9.538115021259956e-06,
857
+ "loss": 1.0715,
858
+ "step": 1190
859
+ },
860
+ {
861
+ "epoch": 2.0326063942409487,
862
+ "grad_norm": 0.9375,
863
+ "learning_rate": 9.52421922774344e-06,
864
+ "loss": 1.0312,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.049544780859623,
869
+ "grad_norm": 0.9609375,
870
+ "learning_rate": 9.510127924773529e-06,
871
+ "loss": 1.0574,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.0664831674782977,
876
+ "grad_norm": 0.95703125,
877
+ "learning_rate": 9.4958417212913e-06,
878
+ "loss": 1.0862,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.0834215540969723,
883
+ "grad_norm": 0.96875,
884
+ "learning_rate": 9.481361234660258e-06,
885
+ "loss": 1.0776,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.100359940715647,
890
+ "grad_norm": 0.95703125,
891
+ "learning_rate": 9.466687090639652e-06,
892
+ "loss": 1.088,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.1172983273343213,
897
+ "grad_norm": 0.9296875,
898
+ "learning_rate": 9.451819923357435e-06,
899
+ "loss": 1.1108,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.134236713952996,
904
+ "grad_norm": 0.9921875,
905
+ "learning_rate": 9.436760375282858e-06,
906
+ "loss": 1.0786,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 2.1511751005716704,
911
+ "grad_norm": 0.87890625,
912
+ "learning_rate": 9.421509097198715e-06,
913
+ "loss": 1.0269,
914
+ "step": 1270
915
+ },
916
+ {
917
+ "epoch": 2.168113487190345,
918
+ "grad_norm": 1.171875,
919
+ "learning_rate": 9.406066748173208e-06,
920
+ "loss": 1.1046,
921
+ "step": 1280
922
+ },
923
+ {
924
+ "epoch": 2.18505187380902,
925
+ "grad_norm": 0.9140625,
926
+ "learning_rate": 9.390433995531473e-06,
927
+ "loss": 1.0651,
928
+ "step": 1290
929
+ },
930
+ {
931
+ "epoch": 2.2019902604276944,
932
+ "grad_norm": 0.91796875,
933
+ "learning_rate": 9.374611514826746e-06,
934
+ "loss": 1.0212,
935
+ "step": 1300
936
+ },
937
+ {
938
+ "epoch": 2.218928647046369,
939
+ "grad_norm": 1.03125,
940
+ "learning_rate": 9.358599989811158e-06,
941
+ "loss": 1.0786,
942
+ "step": 1310
943
+ },
944
+ {
945
+ "epoch": 2.2358670336650435,
946
+ "grad_norm": 1.046875,
947
+ "learning_rate": 9.3424001124062e-06,
948
+ "loss": 1.0125,
949
+ "step": 1320
950
+ },
951
+ {
952
+ "epoch": 2.252805420283718,
953
+ "grad_norm": 0.90234375,
954
+ "learning_rate": 9.326012582672814e-06,
955
+ "loss": 1.0756,
956
+ "step": 1330
957
+ },
958
+ {
959
+ "epoch": 2.2697438069023925,
960
+ "grad_norm": 1.015625,
961
+ "learning_rate": 9.309438108781143e-06,
962
+ "loss": 1.1165,
963
+ "step": 1340
964
+ },
965
+ {
966
+ "epoch": 2.286682193521067,
967
+ "grad_norm": 0.9609375,
968
+ "learning_rate": 9.29267740697993e-06,
969
+ "loss": 1.037,
970
+ "step": 1350
971
+ },
972
+ {
973
+ "epoch": 2.3036205801397416,
974
+ "grad_norm": 1.25,
975
+ "learning_rate": 9.275731201565564e-06,
976
+ "loss": 1.03,
977
+ "step": 1360
978
+ },
979
+ {
980
+ "epoch": 2.320558966758416,
981
+ "grad_norm": 0.93359375,
982
+ "learning_rate": 9.258600224850777e-06,
983
+ "loss": 1.0461,
984
+ "step": 1370
985
+ },
986
+ {
987
+ "epoch": 2.337497353377091,
988
+ "grad_norm": 1.2421875,
989
+ "learning_rate": 9.24128521713301e-06,
990
+ "loss": 1.0065,
991
+ "step": 1380
992
+ },
993
+ {
994
+ "epoch": 2.3544357399957656,
995
+ "grad_norm": 1.0234375,
996
+ "learning_rate": 9.223786926662404e-06,
997
+ "loss": 1.0661,
998
+ "step": 1390
999
+ },
1000
+ {
1001
+ "epoch": 2.37137412661444,
1002
+ "grad_norm": 1.0078125,
1003
+ "learning_rate": 9.20610610960948e-06,
1004
+ "loss": 1.0764,
1005
+ "step": 1400
1006
+ },
1007
+ {
1008
+ "epoch": 2.3883125132331147,
1009
+ "grad_norm": 1.015625,
1010
+ "learning_rate": 9.188243530032458e-06,
1011
+ "loss": 1.0448,
1012
+ "step": 1410
1013
+ },
1014
+ {
1015
+ "epoch": 2.405250899851789,
1016
+ "grad_norm": 0.984375,
1017
+ "learning_rate": 9.170199959844232e-06,
1018
+ "loss": 1.0695,
1019
+ "step": 1420
1020
+ },
1021
+ {
1022
+ "epoch": 2.4221892864704637,
1023
+ "grad_norm": 1.015625,
1024
+ "learning_rate": 9.15197617877902e-06,
1025
+ "loss": 0.9995,
1026
+ "step": 1430
1027
+ },
1028
+ {
1029
+ "epoch": 2.4391276730891382,
1030
+ "grad_norm": 1.015625,
1031
+ "learning_rate": 9.133572974358669e-06,
1032
+ "loss": 1.0307,
1033
+ "step": 1440
1034
+ },
1035
+ {
1036
+ "epoch": 2.4560660597078128,
1037
+ "grad_norm": 1.1328125,
1038
+ "learning_rate": 9.114991141858619e-06,
1039
+ "loss": 1.0004,
1040
+ "step": 1450
1041
+ },
1042
+ {
1043
+ "epoch": 2.4730044463264873,
1044
+ "grad_norm": 1.390625,
1045
+ "learning_rate": 9.096231484273535e-06,
1046
+ "loss": 1.0553,
1047
+ "step": 1460
1048
+ },
1049
+ {
1050
+ "epoch": 2.489942832945162,
1051
+ "grad_norm": 1.1328125,
1052
+ "learning_rate": 9.077294812282615e-06,
1053
+ "loss": 1.0481,
1054
+ "step": 1470
1055
+ },
1056
+ {
1057
+ "epoch": 2.5068812195638364,
1058
+ "grad_norm": 1.203125,
1059
+ "learning_rate": 9.058181944214547e-06,
1060
+ "loss": 1.0438,
1061
+ "step": 1480
1062
+ },
1063
+ {
1064
+ "epoch": 2.523819606182511,
1065
+ "grad_norm": 1.0234375,
1066
+ "learning_rate": 9.038893706012153e-06,
1067
+ "loss": 1.0458,
1068
+ "step": 1490
1069
+ },
1070
+ {
1071
+ "epoch": 2.5407579928011854,
1072
+ "grad_norm": 1.4765625,
1073
+ "learning_rate": 9.01943093119669e-06,
1074
+ "loss": 0.9808,
1075
+ "step": 1500
1076
+ },
1077
+ {
1078
+ "epoch": 2.5407579928011854,
1079
+ "eval_loss": 1.1499994993209839,
1080
+ "eval_runtime": 21.1383,
1081
+ "eval_samples_per_second": 24.836,
1082
+ "eval_steps_per_second": 24.836,
1083
+ "step": 1500
1084
+ },
1085
+ {
1086
+ "epoch": 2.5576963794198604,
1087
+ "grad_norm": 1.4609375,
1088
+ "learning_rate": 8.999794460831836e-06,
1089
+ "loss": 1.0539,
1090
+ "step": 1510
1091
+ },
1092
+ {
1093
+ "epoch": 2.574634766038535,
1094
+ "grad_norm": 1.6640625,
1095
+ "learning_rate": 8.979985143487343e-06,
1096
+ "loss": 1.046,
1097
+ "step": 1520
1098
+ },
1099
+ {
1100
+ "epoch": 2.5915731526572094,
1101
+ "grad_norm": 1.4140625,
1102
+ "learning_rate": 8.960003835202369e-06,
1103
+ "loss": 1.0188,
1104
+ "step": 1530
1105
+ },
1106
+ {
1107
+ "epoch": 2.608511539275884,
1108
+ "grad_norm": 1.453125,
1109
+ "learning_rate": 8.939851399448478e-06,
1110
+ "loss": 1.0423,
1111
+ "step": 1540
1112
+ },
1113
+ {
1114
+ "epoch": 2.6254499258945585,
1115
+ "grad_norm": 2.921875,
1116
+ "learning_rate": 8.919528707092333e-06,
1117
+ "loss": 1.085,
1118
+ "step": 1550
1119
+ },
1120
+ {
1121
+ "epoch": 2.642388312513233,
1122
+ "grad_norm": 2.859375,
1123
+ "learning_rate": 8.899036636358058e-06,
1124
+ "loss": 1.0252,
1125
+ "step": 1560
1126
+ },
1127
+ {
1128
+ "epoch": 2.6593266991319076,
1129
+ "grad_norm": 3.125,
1130
+ "learning_rate": 8.878376072789292e-06,
1131
+ "loss": 1.0246,
1132
+ "step": 1570
1133
+ },
1134
+ {
1135
+ "epoch": 2.6762650857505825,
1136
+ "grad_norm": 2.78125,
1137
+ "learning_rate": 8.857547909210913e-06,
1138
+ "loss": 1.0358,
1139
+ "step": 1580
1140
+ },
1141
+ {
1142
+ "epoch": 2.693203472369257,
1143
+ "grad_norm": 2.59375,
1144
+ "learning_rate": 8.836553045690462e-06,
1145
+ "loss": 1.0746,
1146
+ "step": 1590
1147
+ },
1148
+ {
1149
+ "epoch": 2.7101418589879316,
1150
+ "grad_norm": 3.96875,
1151
+ "learning_rate": 8.81539238949925e-06,
1152
+ "loss": 1.0806,
1153
+ "step": 1600
1154
+ },
1155
+ {
1156
+ "epoch": 2.727080245606606,
1157
+ "grad_norm": 4.15625,
1158
+ "learning_rate": 8.794066855073136e-06,
1159
+ "loss": 0.9917,
1160
+ "step": 1610
1161
+ },
1162
+ {
1163
+ "epoch": 2.7440186322252806,
1164
+ "grad_norm": 4.5625,
1165
+ "learning_rate": 8.772577363973032e-06,
1166
+ "loss": 1.0071,
1167
+ "step": 1620
1168
+ },
1169
+ {
1170
+ "epoch": 2.760957018843955,
1171
+ "grad_norm": 3.25,
1172
+ "learning_rate": 8.750924844845065e-06,
1173
+ "loss": 1.0139,
1174
+ "step": 1630
1175
+ },
1176
+ {
1177
+ "epoch": 2.7778954054626297,
1178
+ "grad_norm": 4.25,
1179
+ "learning_rate": 8.729110233380445e-06,
1180
+ "loss": 1.0684,
1181
+ "step": 1640
1182
+ },
1183
+ {
1184
+ "epoch": 2.7948337920813042,
1185
+ "grad_norm": 9.125,
1186
+ "learning_rate": 8.707134472275042e-06,
1187
+ "loss": 0.9606,
1188
+ "step": 1650
1189
+ },
1190
+ {
1191
+ "epoch": 2.8117721786999788,
1192
+ "grad_norm": 7.78125,
1193
+ "learning_rate": 8.684998511188634e-06,
1194
+ "loss": 1.0529,
1195
+ "step": 1660
1196
+ },
1197
+ {
1198
+ "epoch": 2.8287105653186533,
1199
+ "grad_norm": 7.34375,
1200
+ "learning_rate": 8.662703306703878e-06,
1201
+ "loss": 1.0939,
1202
+ "step": 1670
1203
+ },
1204
+ {
1205
+ "epoch": 2.845648951937328,
1206
+ "grad_norm": 8.375,
1207
+ "learning_rate": 8.640249822284975e-06,
1208
+ "loss": 1.0322,
1209
+ "step": 1680
1210
+ },
1211
+ {
1212
+ "epoch": 2.8625873385560023,
1213
+ "grad_norm": 7.40625,
1214
+ "learning_rate": 8.617639028236021e-06,
1215
+ "loss": 1.0303,
1216
+ "step": 1690
1217
+ },
1218
+ {
1219
+ "epoch": 2.879525725174677,
1220
+ "grad_norm": 2.625,
1221
+ "learning_rate": 8.59487190165909e-06,
1222
+ "loss": 1.0173,
1223
+ "step": 1700
1224
+ },
1225
+ {
1226
+ "epoch": 2.896464111793352,
1227
+ "grad_norm": 2.328125,
1228
+ "learning_rate": 8.571949426412002e-06,
1229
+ "loss": 1.0218,
1230
+ "step": 1710
1231
+ },
1232
+ {
1233
+ "epoch": 2.9134024984120264,
1234
+ "grad_norm": 2.140625,
1235
+ "learning_rate": 8.54887259306581e-06,
1236
+ "loss": 1.0029,
1237
+ "step": 1720
1238
+ },
1239
+ {
1240
+ "epoch": 2.930340885030701,
1241
+ "grad_norm": 2.28125,
1242
+ "learning_rate": 8.525642398861997e-06,
1243
+ "loss": 1.0295,
1244
+ "step": 1730
1245
+ },
1246
+ {
1247
+ "epoch": 2.9472792716493754,
1248
+ "grad_norm": 2.5,
1249
+ "learning_rate": 8.50225984766937e-06,
1250
+ "loss": 1.0432,
1251
+ "step": 1740
1252
+ },
1253
+ {
1254
+ "epoch": 2.96421765826805,
1255
+ "grad_norm": 2.0625,
1256
+ "learning_rate": 8.478725949940687e-06,
1257
+ "loss": 1.026,
1258
+ "step": 1750
1259
+ },
1260
+ {
1261
+ "epoch": 2.9811560448867245,
1262
+ "grad_norm": 2.265625,
1263
+ "learning_rate": 8.455041722668993e-06,
1264
+ "loss": 1.0523,
1265
+ "step": 1760
1266
+ },
1267
+ {
1268
+ "epoch": 2.998094431505399,
1269
+ "grad_norm": 1.8671875,
1270
+ "learning_rate": 8.43120818934367e-06,
1271
+ "loss": 1.0287,
1272
+ "step": 1770
1273
+ },
1274
+ {
1275
+ "epoch": 3.0150328181240735,
1276
+ "grad_norm": 2.109375,
1277
+ "learning_rate": 8.407226379906197e-06,
1278
+ "loss": 0.9998,
1279
+ "step": 1780
1280
+ },
1281
+ {
1282
+ "epoch": 3.031971204742748,
1283
+ "grad_norm": 2.140625,
1284
+ "learning_rate": 8.383097330705664e-06,
1285
+ "loss": 1.0157,
1286
+ "step": 1790
1287
+ },
1288
+ {
1289
+ "epoch": 3.048909591361423,
1290
+ "grad_norm": 1.8828125,
1291
+ "learning_rate": 8.358822084453964e-06,
1292
+ "loss": 0.9514,
1293
+ "step": 1800
1294
+ },
1295
+ {
1296
+ "epoch": 3.0658479779800976,
1297
+ "grad_norm": 1.796875,
1298
+ "learning_rate": 8.334401690180755e-06,
1299
+ "loss": 1.0163,
1300
+ "step": 1810
1301
+ },
1302
+ {
1303
+ "epoch": 3.082786364598772,
1304
+ "grad_norm": 1.8828125,
1305
+ "learning_rate": 8.30983720318811e-06,
1306
+ "loss": 0.969,
1307
+ "step": 1820
1308
+ },
1309
+ {
1310
+ "epoch": 3.0997247512174466,
1311
+ "grad_norm": 1.8203125,
1312
+ "learning_rate": 8.285129685004922e-06,
1313
+ "loss": 0.9769,
1314
+ "step": 1830
1315
+ },
1316
+ {
1317
+ "epoch": 3.116663137836121,
1318
+ "grad_norm": 2.09375,
1319
+ "learning_rate": 8.260280203341026e-06,
1320
+ "loss": 0.9997,
1321
+ "step": 1840
1322
+ },
1323
+ {
1324
+ "epoch": 3.1336015244547957,
1325
+ "grad_norm": 1.828125,
1326
+ "learning_rate": 8.235289832041066e-06,
1327
+ "loss": 0.9577,
1328
+ "step": 1850
1329
+ },
1330
+ {
1331
+ "epoch": 3.15053991107347,
1332
+ "grad_norm": 2.4375,
1333
+ "learning_rate": 8.210159651038081e-06,
1334
+ "loss": 0.9457,
1335
+ "step": 1860
1336
+ },
1337
+ {
1338
+ "epoch": 3.1674782976921447,
1339
+ "grad_norm": 1.7734375,
1340
+ "learning_rate": 8.184890746306848e-06,
1341
+ "loss": 0.9381,
1342
+ "step": 1870
1343
+ },
1344
+ {
1345
+ "epoch": 3.1844166843108193,
1346
+ "grad_norm": 1.96875,
1347
+ "learning_rate": 8.15948420981694e-06,
1348
+ "loss": 0.9709,
1349
+ "step": 1880
1350
+ },
1351
+ {
1352
+ "epoch": 3.201355070929494,
1353
+ "grad_norm": 1.8125,
1354
+ "learning_rate": 8.133941139485551e-06,
1355
+ "loss": 0.9769,
1356
+ "step": 1890
1357
+ },
1358
+ {
1359
+ "epoch": 3.2182934575481683,
1360
+ "grad_norm": 1.875,
1361
+ "learning_rate": 8.108262639130038e-06,
1362
+ "loss": 0.9064,
1363
+ "step": 1900
1364
+ },
1365
+ {
1366
+ "epoch": 3.2352318441668433,
1367
+ "grad_norm": 1.71875,
1368
+ "learning_rate": 8.082449818420227e-06,
1369
+ "loss": 0.9944,
1370
+ "step": 1910
1371
+ },
1372
+ {
1373
+ "epoch": 3.252170230785518,
1374
+ "grad_norm": 2.125,
1375
+ "learning_rate": 8.056503792830458e-06,
1376
+ "loss": 0.9484,
1377
+ "step": 1920
1378
+ },
1379
+ {
1380
+ "epoch": 3.2691086174041923,
1381
+ "grad_norm": 1.8046875,
1382
+ "learning_rate": 8.030425683591391e-06,
1383
+ "loss": 0.9666,
1384
+ "step": 1930
1385
+ },
1386
+ {
1387
+ "epoch": 3.286047004022867,
1388
+ "grad_norm": 1.890625,
1389
+ "learning_rate": 8.004216617641532e-06,
1390
+ "loss": 0.9871,
1391
+ "step": 1940
1392
+ },
1393
+ {
1394
+ "epoch": 3.3029853906415414,
1395
+ "grad_norm": 1.765625,
1396
+ "learning_rate": 7.977877727578556e-06,
1397
+ "loss": 0.9462,
1398
+ "step": 1950
1399
+ },
1400
+ {
1401
+ "epoch": 3.319923777260216,
1402
+ "grad_norm": 2.09375,
1403
+ "learning_rate": 7.951410151610343e-06,
1404
+ "loss": 0.9509,
1405
+ "step": 1960
1406
+ },
1407
+ {
1408
+ "epoch": 3.3368621638788905,
1409
+ "grad_norm": 1.7734375,
1410
+ "learning_rate": 7.92481503350581e-06,
1411
+ "loss": 0.9299,
1412
+ "step": 1970
1413
+ },
1414
+ {
1415
+ "epoch": 3.353800550497565,
1416
+ "grad_norm": 1.734375,
1417
+ "learning_rate": 7.898093522545471e-06,
1418
+ "loss": 0.9824,
1419
+ "step": 1980
1420
+ },
1421
+ {
1422
+ "epoch": 3.3707389371162395,
1423
+ "grad_norm": 1.78125,
1424
+ "learning_rate": 7.871246773471779e-06,
1425
+ "loss": 0.9336,
1426
+ "step": 1990
1427
+ },
1428
+ {
1429
+ "epoch": 3.3876773237349145,
1430
+ "grad_norm": 2.015625,
1431
+ "learning_rate": 7.844275946439216e-06,
1432
+ "loss": 0.9778,
1433
+ "step": 2000
1434
+ },
1435
+ {
1436
+ "epoch": 3.3876773237349145,
1437
+ "eval_loss": 1.1204777956008911,
1438
+ "eval_runtime": 20.947,
1439
+ "eval_samples_per_second": 25.063,
1440
+ "eval_steps_per_second": 25.063,
1441
+ "step": 2000
1442
+ },
1443
+ {
1444
+ "epoch": 3.404615710353589,
1445
+ "grad_norm": 2.359375,
1446
+ "learning_rate": 7.817182206964177e-06,
1447
+ "loss": 0.9817,
1448
+ "step": 2010
1449
+ },
1450
+ {
1451
+ "epoch": 3.4215540969722635,
1452
+ "grad_norm": 2.0625,
1453
+ "learning_rate": 7.789966725874578e-06,
1454
+ "loss": 0.9942,
1455
+ "step": 2020
1456
+ },
1457
+ {
1458
+ "epoch": 3.438492483590938,
1459
+ "grad_norm": 1.734375,
1460
+ "learning_rate": 7.76263067925928e-06,
1461
+ "loss": 0.9783,
1462
+ "step": 2030
1463
+ },
1464
+ {
1465
+ "epoch": 3.4554308702096126,
1466
+ "grad_norm": 1.796875,
1467
+ "learning_rate": 7.735175248417255e-06,
1468
+ "loss": 0.9551,
1469
+ "step": 2040
1470
+ },
1471
+ {
1472
+ "epoch": 3.472369256828287,
1473
+ "grad_norm": 2.046875,
1474
+ "learning_rate": 7.707601619806547e-06,
1475
+ "loss": 0.9592,
1476
+ "step": 2050
1477
+ },
1478
+ {
1479
+ "epoch": 3.4893076434469616,
1480
+ "grad_norm": 2.40625,
1481
+ "learning_rate": 7.679910984992988e-06,
1482
+ "loss": 0.902,
1483
+ "step": 2060
1484
+ },
1485
+ {
1486
+ "epoch": 3.506246030065636,
1487
+ "grad_norm": 2.203125,
1488
+ "learning_rate": 7.652104540598712e-06,
1489
+ "loss": 0.9763,
1490
+ "step": 2070
1491
+ },
1492
+ {
1493
+ "epoch": 3.5231844166843107,
1494
+ "grad_norm": 2.0625,
1495
+ "learning_rate": 7.6241834882504516e-06,
1496
+ "loss": 0.9522,
1497
+ "step": 2080
1498
+ },
1499
+ {
1500
+ "epoch": 3.5401228033029852,
1501
+ "grad_norm": 2.140625,
1502
+ "learning_rate": 7.596149034527594e-06,
1503
+ "loss": 0.992,
1504
+ "step": 2090
1505
+ },
1506
+ {
1507
+ "epoch": 3.5570611899216598,
1508
+ "grad_norm": 1.859375,
1509
+ "learning_rate": 7.5680023909100545e-06,
1510
+ "loss": 0.9366,
1511
+ "step": 2100
1512
+ },
1513
+ {
1514
+ "epoch": 3.5739995765403343,
1515
+ "grad_norm": 1.7421875,
1516
+ "learning_rate": 7.539744773725916e-06,
1517
+ "loss": 0.9888,
1518
+ "step": 2110
1519
+ },
1520
+ {
1521
+ "epoch": 3.5909379631590093,
1522
+ "grad_norm": 1.71875,
1523
+ "learning_rate": 7.511377404098876e-06,
1524
+ "loss": 0.9801,
1525
+ "step": 2120
1526
+ },
1527
+ {
1528
+ "epoch": 3.607876349777684,
1529
+ "grad_norm": 2.0,
1530
+ "learning_rate": 7.482901507895463e-06,
1531
+ "loss": 0.9589,
1532
+ "step": 2130
1533
+ },
1534
+ {
1535
+ "epoch": 3.6248147363963583,
1536
+ "grad_norm": 3.65625,
1537
+ "learning_rate": 7.454318315672074e-06,
1538
+ "loss": 0.9926,
1539
+ "step": 2140
1540
+ },
1541
+ {
1542
+ "epoch": 3.641753123015033,
1543
+ "grad_norm": 1.859375,
1544
+ "learning_rate": 7.425629062621784e-06,
1545
+ "loss": 0.9448,
1546
+ "step": 2150
1547
+ },
1548
+ {
1549
+ "epoch": 3.6586915096337074,
1550
+ "grad_norm": 2.140625,
1551
+ "learning_rate": 7.396834988520989e-06,
1552
+ "loss": 0.9507,
1553
+ "step": 2160
1554
+ },
1555
+ {
1556
+ "epoch": 3.675629896252382,
1557
+ "grad_norm": 2.125,
1558
+ "learning_rate": 7.36793733767581e-06,
1559
+ "loss": 0.9719,
1560
+ "step": 2170
1561
+ },
1562
+ {
1563
+ "epoch": 3.6925682828710564,
1564
+ "grad_norm": 2.34375,
1565
+ "learning_rate": 7.338937358868334e-06,
1566
+ "loss": 0.976,
1567
+ "step": 2180
1568
+ },
1569
+ {
1570
+ "epoch": 3.709506669489731,
1571
+ "grad_norm": 2.28125,
1572
+ "learning_rate": 7.309836305302638e-06,
1573
+ "loss": 0.9431,
1574
+ "step": 2190
1575
+ },
1576
+ {
1577
+ "epoch": 3.726445056108406,
1578
+ "grad_norm": 1.734375,
1579
+ "learning_rate": 7.2806354345506525e-06,
1580
+ "loss": 0.9833,
1581
+ "step": 2200
1582
+ },
1583
+ {
1584
+ "epoch": 3.7433834427270805,
1585
+ "grad_norm": 1.859375,
1586
+ "learning_rate": 7.251336008497793e-06,
1587
+ "loss": 0.9356,
1588
+ "step": 2210
1589
+ },
1590
+ {
1591
+ "epoch": 3.760321829345755,
1592
+ "grad_norm": 1.8203125,
1593
+ "learning_rate": 7.221939293288445e-06,
1594
+ "loss": 0.9911,
1595
+ "step": 2220
1596
+ },
1597
+ {
1598
+ "epoch": 3.7772602159644295,
1599
+ "grad_norm": 1.8671875,
1600
+ "learning_rate": 7.192446559271247e-06,
1601
+ "loss": 0.9569,
1602
+ "step": 2230
1603
+ },
1604
+ {
1605
+ "epoch": 3.794198602583104,
1606
+ "grad_norm": 1.875,
1607
+ "learning_rate": 7.162859080944182e-06,
1608
+ "loss": 0.9907,
1609
+ "step": 2240
1610
+ },
1611
+ {
1612
+ "epoch": 3.8111369892017786,
1613
+ "grad_norm": 1.6484375,
1614
+ "learning_rate": 7.133178136899522e-06,
1615
+ "loss": 0.9672,
1616
+ "step": 2250
1617
+ },
1618
+ {
1619
+ "epoch": 3.828075375820453,
1620
+ "grad_norm": 2.359375,
1621
+ "learning_rate": 7.103405009768554e-06,
1622
+ "loss": 0.9754,
1623
+ "step": 2260
1624
+ },
1625
+ {
1626
+ "epoch": 3.8450137624391276,
1627
+ "grad_norm": 1.7421875,
1628
+ "learning_rate": 7.073540986166166e-06,
1629
+ "loss": 0.9548,
1630
+ "step": 2270
1631
+ },
1632
+ {
1633
+ "epoch": 3.861952149057802,
1634
+ "grad_norm": 1.7421875,
1635
+ "learning_rate": 7.0435873566352434e-06,
1636
+ "loss": 0.9682,
1637
+ "step": 2280
1638
+ },
1639
+ {
1640
+ "epoch": 3.8788905356764767,
1641
+ "grad_norm": 1.8515625,
1642
+ "learning_rate": 7.013545415590897e-06,
1643
+ "loss": 0.8956,
1644
+ "step": 2290
1645
+ },
1646
+ {
1647
+ "epoch": 3.895828922295151,
1648
+ "grad_norm": 1.96875,
1649
+ "learning_rate": 6.983416461264527e-06,
1650
+ "loss": 0.9314,
1651
+ "step": 2300
1652
+ },
1653
+ {
1654
+ "epoch": 3.9127673089138257,
1655
+ "grad_norm": 1.890625,
1656
+ "learning_rate": 6.953201795647728e-06,
1657
+ "loss": 0.9101,
1658
+ "step": 2310
1659
+ },
1660
+ {
1661
+ "epoch": 3.9297056955325003,
1662
+ "grad_norm": 1.921875,
1663
+ "learning_rate": 6.922902724436016e-06,
1664
+ "loss": 0.9463,
1665
+ "step": 2320
1666
+ },
1667
+ {
1668
+ "epoch": 3.9466440821511752,
1669
+ "grad_norm": 1.8984375,
1670
+ "learning_rate": 6.892520556972404e-06,
1671
+ "loss": 0.9443,
1672
+ "step": 2330
1673
+ },
1674
+ {
1675
+ "epoch": 3.9635824687698498,
1676
+ "grad_norm": 1.8125,
1677
+ "learning_rate": 6.86205660619083e-06,
1678
+ "loss": 0.9371,
1679
+ "step": 2340
1680
+ },
1681
+ {
1682
+ "epoch": 3.9805208553885243,
1683
+ "grad_norm": 1.9375,
1684
+ "learning_rate": 6.8315121885594105e-06,
1685
+ "loss": 0.95,
1686
+ "step": 2350
1687
+ },
1688
+ {
1689
+ "epoch": 3.997459242007199,
1690
+ "grad_norm": 1.9140625,
1691
+ "learning_rate": 6.800888624023552e-06,
1692
+ "loss": 0.9412,
1693
+ "step": 2360
1694
+ },
1695
+ {
1696
+ "epoch": 4.014397628625874,
1697
+ "grad_norm": 1.59375,
1698
+ "learning_rate": 6.770187235948916e-06,
1699
+ "loss": 0.8627,
1700
+ "step": 2370
1701
+ },
1702
+ {
1703
+ "epoch": 4.031336015244548,
1704
+ "grad_norm": 1.671875,
1705
+ "learning_rate": 6.739409351064225e-06,
1706
+ "loss": 0.8663,
1707
+ "step": 2380
1708
+ },
1709
+ {
1710
+ "epoch": 4.048274401863223,
1711
+ "grad_norm": 1.8046875,
1712
+ "learning_rate": 6.708556299403935e-06,
1713
+ "loss": 0.8087,
1714
+ "step": 2390
1715
+ },
1716
+ {
1717
+ "epoch": 4.065212788481897,
1718
+ "grad_norm": 1.7578125,
1719
+ "learning_rate": 6.6776294142507535e-06,
1720
+ "loss": 0.8501,
1721
+ "step": 2400
1722
+ },
1723
+ {
1724
+ "epoch": 4.082151175100572,
1725
+ "grad_norm": 1.6328125,
1726
+ "learning_rate": 6.646630032078024e-06,
1727
+ "loss": 0.854,
1728
+ "step": 2410
1729
+ },
1730
+ {
1731
+ "epoch": 4.099089561719246,
1732
+ "grad_norm": 1.5,
1733
+ "learning_rate": 6.615559492491981e-06,
1734
+ "loss": 0.884,
1735
+ "step": 2420
1736
+ },
1737
+ {
1738
+ "epoch": 4.116027948337921,
1739
+ "grad_norm": 1.890625,
1740
+ "learning_rate": 6.584419138173846e-06,
1741
+ "loss": 0.8693,
1742
+ "step": 2430
1743
+ },
1744
+ {
1745
+ "epoch": 4.1329663349565955,
1746
+ "grad_norm": 1.625,
1747
+ "learning_rate": 6.553210314821814e-06,
1748
+ "loss": 0.8397,
1749
+ "step": 2440
1750
+ },
1751
+ {
1752
+ "epoch": 4.14990472157527,
1753
+ "grad_norm": 1.7265625,
1754
+ "learning_rate": 6.521934371092901e-06,
1755
+ "loss": 0.8355,
1756
+ "step": 2450
1757
+ },
1758
+ {
1759
+ "epoch": 4.1668431081939445,
1760
+ "grad_norm": 1.5,
1761
+ "learning_rate": 6.490592658544661e-06,
1762
+ "loss": 0.8784,
1763
+ "step": 2460
1764
+ },
1765
+ {
1766
+ "epoch": 4.183781494812619,
1767
+ "grad_norm": 1.484375,
1768
+ "learning_rate": 6.459186531576772e-06,
1769
+ "loss": 0.8902,
1770
+ "step": 2470
1771
+ },
1772
+ {
1773
+ "epoch": 4.200719881431294,
1774
+ "grad_norm": 1.640625,
1775
+ "learning_rate": 6.427717347372523e-06,
1776
+ "loss": 0.8175,
1777
+ "step": 2480
1778
+ },
1779
+ {
1780
+ "epoch": 4.217658268049968,
1781
+ "grad_norm": 1.7109375,
1782
+ "learning_rate": 6.396186465840152e-06,
1783
+ "loss": 0.8717,
1784
+ "step": 2490
1785
+ },
1786
+ {
1787
+ "epoch": 4.234596654668643,
1788
+ "grad_norm": 1.5234375,
1789
+ "learning_rate": 6.364595249554084e-06,
1790
+ "loss": 0.8815,
1791
+ "step": 2500
1792
+ },
1793
+ {
1794
+ "epoch": 4.234596654668643,
1795
+ "eval_loss": 1.09398353099823,
1796
+ "eval_runtime": 20.9341,
1797
+ "eval_samples_per_second": 25.079,
1798
+ "eval_steps_per_second": 25.079,
1799
+ "step": 2500
1800
+ },
1801
+ {
1802
+ "epoch": 4.251535041287317,
1803
+ "grad_norm": 1.4296875,
1804
+ "learning_rate": 6.332945063696049e-06,
1805
+ "loss": 0.8658,
1806
+ "step": 2510
1807
+ },
1808
+ {
1809
+ "epoch": 4.268473427905992,
1810
+ "grad_norm": 1.3828125,
1811
+ "learning_rate": 6.3012372759960825e-06,
1812
+ "loss": 0.8465,
1813
+ "step": 2520
1814
+ },
1815
+ {
1816
+ "epoch": 4.285411814524666,
1817
+ "grad_norm": 1.5234375,
1818
+ "learning_rate": 6.26947325667343e-06,
1819
+ "loss": 0.8707,
1820
+ "step": 2530
1821
+ },
1822
+ {
1823
+ "epoch": 4.302350201143341,
1824
+ "grad_norm": 1.4140625,
1825
+ "learning_rate": 6.237654378377324e-06,
1826
+ "loss": 0.8921,
1827
+ "step": 2540
1828
+ },
1829
+ {
1830
+ "epoch": 4.319288587762015,
1831
+ "grad_norm": 1.5390625,
1832
+ "learning_rate": 6.2057820161276715e-06,
1833
+ "loss": 0.8703,
1834
+ "step": 2550
1835
+ },
1836
+ {
1837
+ "epoch": 4.33622697438069,
1838
+ "grad_norm": 1.2734375,
1839
+ "learning_rate": 6.173857547255634e-06,
1840
+ "loss": 0.8467,
1841
+ "step": 2560
1842
+ },
1843
+ {
1844
+ "epoch": 4.353165360999364,
1845
+ "grad_norm": 1.578125,
1846
+ "learning_rate": 6.141882351344106e-06,
1847
+ "loss": 0.8581,
1848
+ "step": 2570
1849
+ },
1850
+ {
1851
+ "epoch": 4.37010374761804,
1852
+ "grad_norm": 1.4609375,
1853
+ "learning_rate": 6.1098578101680986e-06,
1854
+ "loss": 0.8617,
1855
+ "step": 2580
1856
+ },
1857
+ {
1858
+ "epoch": 4.387042134236714,
1859
+ "grad_norm": 1.3046875,
1860
+ "learning_rate": 6.077785307635027e-06,
1861
+ "loss": 0.8082,
1862
+ "step": 2590
1863
+ },
1864
+ {
1865
+ "epoch": 4.403980520855389,
1866
+ "grad_norm": 1.34375,
1867
+ "learning_rate": 6.045666229724909e-06,
1868
+ "loss": 0.8048,
1869
+ "step": 2600
1870
+ },
1871
+ {
1872
+ "epoch": 4.420918907474063,
1873
+ "grad_norm": 1.4453125,
1874
+ "learning_rate": 6.013501964430468e-06,
1875
+ "loss": 0.8537,
1876
+ "step": 2610
1877
+ },
1878
+ {
1879
+ "epoch": 4.437857294092738,
1880
+ "grad_norm": 1.3359375,
1881
+ "learning_rate": 5.981293901697153e-06,
1882
+ "loss": 0.8683,
1883
+ "step": 2620
1884
+ },
1885
+ {
1886
+ "epoch": 4.454795680711412,
1887
+ "grad_norm": 1.1953125,
1888
+ "learning_rate": 5.9490434333630735e-06,
1889
+ "loss": 0.8599,
1890
+ "step": 2630
1891
+ },
1892
+ {
1893
+ "epoch": 4.471734067330087,
1894
+ "grad_norm": 1.3203125,
1895
+ "learning_rate": 5.916751953098854e-06,
1896
+ "loss": 0.8811,
1897
+ "step": 2640
1898
+ },
1899
+ {
1900
+ "epoch": 4.4886724539487615,
1901
+ "grad_norm": 1.21875,
1902
+ "learning_rate": 5.884420856347406e-06,
1903
+ "loss": 0.8891,
1904
+ "step": 2650
1905
+ },
1906
+ {
1907
+ "epoch": 4.505610840567436,
1908
+ "grad_norm": 1.3515625,
1909
+ "learning_rate": 5.852051540263628e-06,
1910
+ "loss": 0.8634,
1911
+ "step": 2660
1912
+ },
1913
+ {
1914
+ "epoch": 4.5225492271861105,
1915
+ "grad_norm": 1.28125,
1916
+ "learning_rate": 5.819645403654027e-06,
1917
+ "loss": 0.842,
1918
+ "step": 2670
1919
+ },
1920
+ {
1921
+ "epoch": 4.539487613804785,
1922
+ "grad_norm": 1.6484375,
1923
+ "learning_rate": 5.787203846916273e-06,
1924
+ "loss": 0.8485,
1925
+ "step": 2680
1926
+ },
1927
+ {
1928
+ "epoch": 4.55642600042346,
1929
+ "grad_norm": 1.265625,
1930
+ "learning_rate": 5.754728271978675e-06,
1931
+ "loss": 0.883,
1932
+ "step": 2690
1933
+ },
1934
+ {
1935
+ "epoch": 4.573364387042134,
1936
+ "grad_norm": 1.2265625,
1937
+ "learning_rate": 5.722220082239608e-06,
1938
+ "loss": 0.8457,
1939
+ "step": 2700
1940
+ },
1941
+ {
1942
+ "epoch": 4.590302773660809,
1943
+ "grad_norm": 1.1640625,
1944
+ "learning_rate": 5.689680682506861e-06,
1945
+ "loss": 0.8999,
1946
+ "step": 2710
1947
+ },
1948
+ {
1949
+ "epoch": 4.607241160279483,
1950
+ "grad_norm": 1.171875,
1951
+ "learning_rate": 5.657111478936926e-06,
1952
+ "loss": 0.8391,
1953
+ "step": 2720
1954
+ },
1955
+ {
1956
+ "epoch": 4.624179546898158,
1957
+ "grad_norm": 1.2265625,
1958
+ "learning_rate": 5.6245138789742444e-06,
1959
+ "loss": 0.8313,
1960
+ "step": 2730
1961
+ },
1962
+ {
1963
+ "epoch": 4.641117933516832,
1964
+ "grad_norm": 1.1640625,
1965
+ "learning_rate": 5.591889291290373e-06,
1966
+ "loss": 0.8709,
1967
+ "step": 2740
1968
+ },
1969
+ {
1970
+ "epoch": 4.658056320135507,
1971
+ "grad_norm": 0.9921875,
1972
+ "learning_rate": 5.559239125723119e-06,
1973
+ "loss": 0.8507,
1974
+ "step": 2750
1975
+ },
1976
+ {
1977
+ "epoch": 4.674994706754182,
1978
+ "grad_norm": 0.96484375,
1979
+ "learning_rate": 5.5265647932156066e-06,
1980
+ "loss": 0.9057,
1981
+ "step": 2760
1982
+ },
1983
+ {
1984
+ "epoch": 4.691933093372857,
1985
+ "grad_norm": 1.1171875,
1986
+ "learning_rate": 5.493867705755312e-06,
1987
+ "loss": 0.8386,
1988
+ "step": 2770
1989
+ },
1990
+ {
1991
+ "epoch": 4.708871479991531,
1992
+ "grad_norm": 1.0,
1993
+ "learning_rate": 5.461149276313046e-06,
1994
+ "loss": 0.9338,
1995
+ "step": 2780
1996
+ },
1997
+ {
1998
+ "epoch": 4.725809866610206,
1999
+ "grad_norm": 1.0234375,
2000
+ "learning_rate": 5.428410918781885e-06,
2001
+ "loss": 0.8176,
2002
+ "step": 2790
2003
+ },
2004
+ {
2005
+ "epoch": 4.74274825322888,
2006
+ "grad_norm": 1.046875,
2007
+ "learning_rate": 5.395654047916083e-06,
2008
+ "loss": 0.8609,
2009
+ "step": 2800
2010
+ },
2011
+ {
2012
+ "epoch": 4.759686639847555,
2013
+ "grad_norm": 1.09375,
2014
+ "learning_rate": 5.362880079269921e-06,
2015
+ "loss": 0.8494,
2016
+ "step": 2810
2017
+ },
2018
+ {
2019
+ "epoch": 4.776625026466229,
2020
+ "grad_norm": 1.1953125,
2021
+ "learning_rate": 5.330090429136553e-06,
2022
+ "loss": 0.8254,
2023
+ "step": 2820
2024
+ },
2025
+ {
2026
+ "epoch": 4.793563413084904,
2027
+ "grad_norm": 1.2890625,
2028
+ "learning_rate": 5.297286514486785e-06,
2029
+ "loss": 0.8689,
2030
+ "step": 2830
2031
+ },
2032
+ {
2033
+ "epoch": 4.810501799703578,
2034
+ "grad_norm": 1.125,
2035
+ "learning_rate": 5.26446975290785e-06,
2036
+ "loss": 0.8483,
2037
+ "step": 2840
2038
+ },
2039
+ {
2040
+ "epoch": 4.827440186322253,
2041
+ "grad_norm": 0.98046875,
2042
+ "learning_rate": 5.23164156254215e-06,
2043
+ "loss": 0.8436,
2044
+ "step": 2850
2045
+ },
2046
+ {
2047
+ "epoch": 4.844378572940927,
2048
+ "grad_norm": 0.91796875,
2049
+ "learning_rate": 5.19880336202597e-06,
2050
+ "loss": 0.8584,
2051
+ "step": 2860
2052
+ },
2053
+ {
2054
+ "epoch": 4.861316959559602,
2055
+ "grad_norm": 1.2265625,
2056
+ "learning_rate": 5.165956570428173e-06,
2057
+ "loss": 0.8122,
2058
+ "step": 2870
2059
+ },
2060
+ {
2061
+ "epoch": 4.8782553461782765,
2062
+ "grad_norm": 1.0703125,
2063
+ "learning_rate": 5.133102607188875e-06,
2064
+ "loss": 0.8705,
2065
+ "step": 2880
2066
+ },
2067
+ {
2068
+ "epoch": 4.895193732796951,
2069
+ "grad_norm": 1.34375,
2070
+ "learning_rate": 5.100242892058108e-06,
2071
+ "loss": 0.8788,
2072
+ "step": 2890
2073
+ },
2074
+ {
2075
+ "epoch": 4.9121321194156256,
2076
+ "grad_norm": 1.015625,
2077
+ "learning_rate": 5.067378845034468e-06,
2078
+ "loss": 0.8663,
2079
+ "step": 2900
2080
+ },
2081
+ {
2082
+ "epoch": 4.9290705060343,
2083
+ "grad_norm": 1.046875,
2084
+ "learning_rate": 5.034511886303746e-06,
2085
+ "loss": 0.8706,
2086
+ "step": 2910
2087
+ },
2088
+ {
2089
+ "epoch": 4.946008892652975,
2090
+ "grad_norm": 1.1171875,
2091
+ "learning_rate": 5.00164343617756e-06,
2092
+ "loss": 0.845,
2093
+ "step": 2920
2094
+ },
2095
+ {
2096
+ "epoch": 4.962947279271649,
2097
+ "grad_norm": 1.0078125,
2098
+ "learning_rate": 4.968774915031982e-06,
2099
+ "loss": 0.8165,
2100
+ "step": 2930
2101
+ },
2102
+ {
2103
+ "epoch": 4.979885665890324,
2104
+ "grad_norm": 1.3125,
2105
+ "learning_rate": 4.9359077432461455e-06,
2106
+ "loss": 0.8719,
2107
+ "step": 2940
2108
+ },
2109
+ {
2110
+ "epoch": 4.996824052508998,
2111
+ "grad_norm": 0.88671875,
2112
+ "learning_rate": 4.903043341140879e-06,
2113
+ "loss": 0.8579,
2114
+ "step": 2950
2115
+ },
2116
+ {
2117
+ "epoch": 5.013762439127673,
2118
+ "grad_norm": 0.921875,
2119
+ "learning_rate": 4.870183128917318e-06,
2120
+ "loss": 0.7986,
2121
+ "step": 2960
2122
+ },
2123
+ {
2124
+ "epoch": 5.030700825746347,
2125
+ "grad_norm": 1.140625,
2126
+ "learning_rate": 4.837328526595539e-06,
2127
+ "loss": 0.8119,
2128
+ "step": 2970
2129
+ },
2130
+ {
2131
+ "epoch": 5.047639212365023,
2132
+ "grad_norm": 0.97265625,
2133
+ "learning_rate": 4.804480953953193e-06,
2134
+ "loss": 0.8013,
2135
+ "step": 2980
2136
+ },
2137
+ {
2138
+ "epoch": 5.064577598983697,
2139
+ "grad_norm": 0.9296875,
2140
+ "learning_rate": 4.771641830464146e-06,
2141
+ "loss": 0.7954,
2142
+ "step": 2990
2143
+ },
2144
+ {
2145
+ "epoch": 5.081515985602372,
2146
+ "grad_norm": 1.046875,
2147
+ "learning_rate": 4.738812575237148e-06,
2148
+ "loss": 0.8159,
2149
+ "step": 3000
2150
+ },
2151
+ {
2152
+ "epoch": 5.081515985602372,
2153
+ "eval_loss": 1.0747902393341064,
2154
+ "eval_runtime": 20.9737,
2155
+ "eval_samples_per_second": 25.031,
2156
+ "eval_steps_per_second": 25.031,
2157
+ "step": 3000
2158
+ },
2159
+ {
2160
+ "epoch": 5.098454372221046,
2161
+ "grad_norm": 1.0625,
2162
+ "learning_rate": 4.705994606954497e-06,
2163
+ "loss": 0.7888,
2164
+ "step": 3010
2165
+ },
2166
+ {
2167
+ "epoch": 5.115392758839721,
2168
+ "grad_norm": 1.09375,
2169
+ "learning_rate": 4.673189343810747e-06,
2170
+ "loss": 0.8088,
2171
+ "step": 3020
2172
+ },
2173
+ {
2174
+ "epoch": 5.132331145458395,
2175
+ "grad_norm": 1.0,
2176
+ "learning_rate": 4.640398203451402e-06,
2177
+ "loss": 0.7762,
2178
+ "step": 3030
2179
+ },
2180
+ {
2181
+ "epoch": 5.14926953207707,
2182
+ "grad_norm": 1.078125,
2183
+ "learning_rate": 4.607622602911668e-06,
2184
+ "loss": 0.8108,
2185
+ "step": 3040
2186
+ },
2187
+ {
2188
+ "epoch": 5.166207918695744,
2189
+ "grad_norm": 1.1171875,
2190
+ "learning_rate": 4.574863958555215e-06,
2191
+ "loss": 0.7981,
2192
+ "step": 3050
2193
+ },
2194
+ {
2195
+ "epoch": 5.183146305314419,
2196
+ "grad_norm": 1.1953125,
2197
+ "learning_rate": 4.542123686012969e-06,
2198
+ "loss": 0.8295,
2199
+ "step": 3060
2200
+ },
2201
+ {
2202
+ "epoch": 5.200084691933093,
2203
+ "grad_norm": 1.1875,
2204
+ "learning_rate": 4.509403200121936e-06,
2205
+ "loss": 0.7986,
2206
+ "step": 3070
2207
+ },
2208
+ {
2209
+ "epoch": 5.217023078551768,
2210
+ "grad_norm": 1.1875,
2211
+ "learning_rate": 4.47670391486406e-06,
2212
+ "loss": 0.792,
2213
+ "step": 3080
2214
+ },
2215
+ {
2216
+ "epoch": 5.2339614651704425,
2217
+ "grad_norm": 1.1484375,
2218
+ "learning_rate": 4.44402724330513e-06,
2219
+ "loss": 0.8072,
2220
+ "step": 3090
2221
+ },
2222
+ {
2223
+ "epoch": 5.250899851789117,
2224
+ "grad_norm": 1.3203125,
2225
+ "learning_rate": 4.4113745975337e-06,
2226
+ "loss": 0.7877,
2227
+ "step": 3100
2228
+ },
2229
+ {
2230
+ "epoch": 5.2678382384077915,
2231
+ "grad_norm": 1.4921875,
2232
+ "learning_rate": 4.378747388600075e-06,
2233
+ "loss": 0.7823,
2234
+ "step": 3110
2235
+ },
2236
+ {
2237
+ "epoch": 5.284776625026466,
2238
+ "grad_norm": 1.40625,
2239
+ "learning_rate": 4.346147026455334e-06,
2240
+ "loss": 0.7957,
2241
+ "step": 3120
2242
+ },
2243
+ {
2244
+ "epoch": 5.301715011645141,
2245
+ "grad_norm": 1.390625,
2246
+ "learning_rate": 4.313574919890402e-06,
2247
+ "loss": 0.7562,
2248
+ "step": 3130
2249
+ },
2250
+ {
2251
+ "epoch": 5.318653398263815,
2252
+ "grad_norm": 1.3671875,
2253
+ "learning_rate": 4.281032476475165e-06,
2254
+ "loss": 0.7981,
2255
+ "step": 3140
2256
+ },
2257
+ {
2258
+ "epoch": 5.33559178488249,
2259
+ "grad_norm": 2.265625,
2260
+ "learning_rate": 4.248521102497649e-06,
2261
+ "loss": 0.7806,
2262
+ "step": 3150
2263
+ },
2264
+ {
2265
+ "epoch": 5.352530171501164,
2266
+ "grad_norm": 2.578125,
2267
+ "learning_rate": 4.216042202903246e-06,
2268
+ "loss": 0.848,
2269
+ "step": 3160
2270
+ },
2271
+ {
2272
+ "epoch": 5.369468558119839,
2273
+ "grad_norm": 2.171875,
2274
+ "learning_rate": 4.183597181234001e-06,
2275
+ "loss": 0.7903,
2276
+ "step": 3170
2277
+ },
2278
+ {
2279
+ "epoch": 5.386406944738514,
2280
+ "grad_norm": 2.515625,
2281
+ "learning_rate": 4.151187439567961e-06,
2282
+ "loss": 0.7914,
2283
+ "step": 3180
2284
+ },
2285
+ {
2286
+ "epoch": 5.403345331357189,
2287
+ "grad_norm": 2.25,
2288
+ "learning_rate": 4.118814378458582e-06,
2289
+ "loss": 0.7983,
2290
+ "step": 3190
2291
+ },
2292
+ {
2293
+ "epoch": 5.420283717975863,
2294
+ "grad_norm": 3.09375,
2295
+ "learning_rate": 4.086479396874206e-06,
2296
+ "loss": 0.7606,
2297
+ "step": 3200
2298
+ },
2299
+ {
2300
+ "epoch": 5.437222104594538,
2301
+ "grad_norm": 2.828125,
2302
+ "learning_rate": 4.054183892137611e-06,
2303
+ "loss": 0.7947,
2304
+ "step": 3210
2305
+ },
2306
+ {
2307
+ "epoch": 5.454160491213212,
2308
+ "grad_norm": 4.375,
2309
+ "learning_rate": 4.021929259865624e-06,
2310
+ "loss": 0.7764,
2311
+ "step": 3220
2312
+ },
2313
+ {
2314
+ "epoch": 5.471098877831887,
2315
+ "grad_norm": 4.46875,
2316
+ "learning_rate": 3.989716893908807e-06,
2317
+ "loss": 0.7829,
2318
+ "step": 3230
2319
+ },
2320
+ {
2321
+ "epoch": 5.488037264450561,
2322
+ "grad_norm": 3.5625,
2323
+ "learning_rate": 3.9575481862912335e-06,
2324
+ "loss": 0.7811,
2325
+ "step": 3240
2326
+ },
2327
+ {
2328
+ "epoch": 5.504975651069236,
2329
+ "grad_norm": 8.125,
2330
+ "learning_rate": 3.925424527150321e-06,
2331
+ "loss": 0.804,
2332
+ "step": 3250
2333
+ },
2334
+ {
2335
+ "epoch": 5.52191403768791,
2336
+ "grad_norm": 7.96875,
2337
+ "learning_rate": 3.893347304676766e-06,
2338
+ "loss": 0.7975,
2339
+ "step": 3260
2340
+ },
2341
+ {
2342
+ "epoch": 5.538852424306585,
2343
+ "grad_norm": 7.6875,
2344
+ "learning_rate": 3.861317905054551e-06,
2345
+ "loss": 0.7812,
2346
+ "step": 3270
2347
+ },
2348
+ {
2349
+ "epoch": 5.555790810925259,
2350
+ "grad_norm": 8.0625,
2351
+ "learning_rate": 3.8293377124010476e-06,
2352
+ "loss": 0.8092,
2353
+ "step": 3280
2354
+ },
2355
+ {
2356
+ "epoch": 5.572729197543934,
2357
+ "grad_norm": 8.0625,
2358
+ "learning_rate": 3.797408108707193e-06,
2359
+ "loss": 0.8141,
2360
+ "step": 3290
2361
+ },
2362
+ {
2363
+ "epoch": 5.5896675841626084,
2364
+ "grad_norm": 2.125,
2365
+ "learning_rate": 3.7655304737777775e-06,
2366
+ "loss": 0.815,
2367
+ "step": 3300
2368
+ },
2369
+ {
2370
+ "epoch": 5.606605970781283,
2371
+ "grad_norm": 2.109375,
2372
+ "learning_rate": 3.733706185171819e-06,
2373
+ "loss": 0.7505,
2374
+ "step": 3310
2375
+ },
2376
+ {
2377
+ "epoch": 5.6235443573999575,
2378
+ "grad_norm": 1.96875,
2379
+ "learning_rate": 3.701936618143025e-06,
2380
+ "loss": 0.7535,
2381
+ "step": 3320
2382
+ },
2383
+ {
2384
+ "epoch": 5.640482744018632,
2385
+ "grad_norm": 2.46875,
2386
+ "learning_rate": 3.6702231455803662e-06,
2387
+ "loss": 0.7703,
2388
+ "step": 3330
2389
+ },
2390
+ {
2391
+ "epoch": 5.657421130637307,
2392
+ "grad_norm": 2.15625,
2393
+ "learning_rate": 3.6385671379487496e-06,
2394
+ "loss": 0.7493,
2395
+ "step": 3340
2396
+ },
2397
+ {
2398
+ "epoch": 5.674359517255981,
2399
+ "grad_norm": 1.875,
2400
+ "learning_rate": 3.606969963229798e-06,
2401
+ "loss": 0.8281,
2402
+ "step": 3350
2403
+ },
2404
+ {
2405
+ "epoch": 5.691297903874656,
2406
+ "grad_norm": 1.9140625,
2407
+ "learning_rate": 3.5754329868627256e-06,
2408
+ "loss": 0.8207,
2409
+ "step": 3360
2410
+ },
2411
+ {
2412
+ "epoch": 5.70823629049333,
2413
+ "grad_norm": 2.046875,
2414
+ "learning_rate": 3.5439575716853414e-06,
2415
+ "loss": 0.8263,
2416
+ "step": 3370
2417
+ },
2418
+ {
2419
+ "epoch": 5.725174677112005,
2420
+ "grad_norm": 2.015625,
2421
+ "learning_rate": 3.5125450778751453e-06,
2422
+ "loss": 0.8106,
2423
+ "step": 3380
2424
+ },
2425
+ {
2426
+ "epoch": 5.742113063730679,
2427
+ "grad_norm": 2.125,
2428
+ "learning_rate": 3.4811968628905646e-06,
2429
+ "loss": 0.7993,
2430
+ "step": 3390
2431
+ },
2432
+ {
2433
+ "epoch": 5.759051450349354,
2434
+ "grad_norm": 1.84375,
2435
+ "learning_rate": 3.4499142814122766e-06,
2436
+ "loss": 0.7784,
2437
+ "step": 3400
2438
+ },
2439
+ {
2440
+ "epoch": 5.775989836968029,
2441
+ "grad_norm": 1.7890625,
2442
+ "learning_rate": 3.418698685284676e-06,
2443
+ "loss": 0.7762,
2444
+ "step": 3410
2445
+ },
2446
+ {
2447
+ "epoch": 5.792928223586704,
2448
+ "grad_norm": 1.8984375,
2449
+ "learning_rate": 3.387551423457456e-06,
2450
+ "loss": 0.7905,
2451
+ "step": 3420
2452
+ },
2453
+ {
2454
+ "epoch": 5.809866610205378,
2455
+ "grad_norm": 1.9765625,
2456
+ "learning_rate": 3.356473841927313e-06,
2457
+ "loss": 0.8273,
2458
+ "step": 3430
2459
+ },
2460
+ {
2461
+ "epoch": 5.826804996824053,
2462
+ "grad_norm": 2.046875,
2463
+ "learning_rate": 3.3254672836797814e-06,
2464
+ "loss": 0.7962,
2465
+ "step": 3440
2466
+ },
2467
+ {
2468
+ "epoch": 5.843743383442727,
2469
+ "grad_norm": 2.03125,
2470
+ "learning_rate": 3.2945330886311964e-06,
2471
+ "loss": 0.8146,
2472
+ "step": 3450
2473
+ },
2474
+ {
2475
+ "epoch": 5.860681770061402,
2476
+ "grad_norm": 1.9765625,
2477
+ "learning_rate": 3.263672593570797e-06,
2478
+ "loss": 0.8032,
2479
+ "step": 3460
2480
+ },
2481
+ {
2482
+ "epoch": 5.877620156680076,
2483
+ "grad_norm": 1.84375,
2484
+ "learning_rate": 3.23288713210295e-06,
2485
+ "loss": 0.7997,
2486
+ "step": 3470
2487
+ },
2488
+ {
2489
+ "epoch": 5.894558543298751,
2490
+ "grad_norm": 1.8828125,
2491
+ "learning_rate": 3.2021780345895216e-06,
2492
+ "loss": 0.8009,
2493
+ "step": 3480
2494
+ },
2495
+ {
2496
+ "epoch": 5.911496929917425,
2497
+ "grad_norm": 1.953125,
2498
+ "learning_rate": 3.1715466280923924e-06,
2499
+ "loss": 0.8302,
2500
+ "step": 3490
2501
+ },
2502
+ {
2503
+ "epoch": 5.9284353165361,
2504
+ "grad_norm": 2.359375,
2505
+ "learning_rate": 3.1409942363161037e-06,
2506
+ "loss": 0.8317,
2507
+ "step": 3500
2508
+ },
2509
+ {
2510
+ "epoch": 5.9284353165361,
2511
+ "eval_loss": 1.0828534364700317,
2512
+ "eval_runtime": 21.0141,
2513
+ "eval_samples_per_second": 24.983,
2514
+ "eval_steps_per_second": 24.983,
2515
+ "step": 3500
2516
+ },
2517
+ {
2518
+ "epoch": 5.945373703154774,
2519
+ "grad_norm": 2.125,
2520
+ "learning_rate": 3.1105221795506584e-06,
2521
+ "loss": 0.8026,
2522
+ "step": 3510
2523
+ },
2524
+ {
2525
+ "epoch": 5.962312089773449,
2526
+ "grad_norm": 2.046875,
2527
+ "learning_rate": 3.080131774614464e-06,
2528
+ "loss": 0.8209,
2529
+ "step": 3520
2530
+ },
2531
+ {
2532
+ "epoch": 5.9792504763921235,
2533
+ "grad_norm": 1.8515625,
2534
+ "learning_rate": 3.049824334797431e-06,
2535
+ "loss": 0.8086,
2536
+ "step": 3530
2537
+ },
2538
+ {
2539
+ "epoch": 5.996188863010798,
2540
+ "grad_norm": 2.015625,
2541
+ "learning_rate": 3.019601169804216e-06,
2542
+ "loss": 0.7651,
2543
+ "step": 3540
2544
+ },
2545
+ {
2546
+ "epoch": 6.0131272496294725,
2547
+ "grad_norm": 1.703125,
2548
+ "learning_rate": 2.9894635856976268e-06,
2549
+ "loss": 0.7734,
2550
+ "step": 3550
2551
+ },
2552
+ {
2553
+ "epoch": 6.030065636248147,
2554
+ "grad_norm": 1.8671875,
2555
+ "learning_rate": 2.959412884842181e-06,
2556
+ "loss": 0.7799,
2557
+ "step": 3560
2558
+ },
2559
+ {
2560
+ "epoch": 6.047004022866822,
2561
+ "grad_norm": 1.921875,
2562
+ "learning_rate": 2.929450365847828e-06,
2563
+ "loss": 0.7448,
2564
+ "step": 3570
2565
+ },
2566
+ {
2567
+ "epoch": 6.063942409485496,
2568
+ "grad_norm": 2.0,
2569
+ "learning_rate": 2.899577323513829e-06,
2570
+ "loss": 0.7354,
2571
+ "step": 3580
2572
+ },
2573
+ {
2574
+ "epoch": 6.080880796104171,
2575
+ "grad_norm": 2.109375,
2576
+ "learning_rate": 2.8697950487728e-06,
2577
+ "loss": 0.7585,
2578
+ "step": 3590
2579
+ },
2580
+ {
2581
+ "epoch": 6.097819182722846,
2582
+ "grad_norm": 1.828125,
2583
+ "learning_rate": 2.8401048286349353e-06,
2584
+ "loss": 0.7635,
2585
+ "step": 3600
2586
+ },
2587
+ {
2588
+ "epoch": 6.114757569341521,
2589
+ "grad_norm": 1.84375,
2590
+ "learning_rate": 2.8105079461323818e-06,
2591
+ "loss": 0.7781,
2592
+ "step": 3610
2593
+ },
2594
+ {
2595
+ "epoch": 6.131695955960195,
2596
+ "grad_norm": 1.8359375,
2597
+ "learning_rate": 2.7810056802637995e-06,
2598
+ "loss": 0.7646,
2599
+ "step": 3620
2600
+ },
2601
+ {
2602
+ "epoch": 6.14863434257887,
2603
+ "grad_norm": 1.96875,
2604
+ "learning_rate": 2.751599305939082e-06,
2605
+ "loss": 0.7657,
2606
+ "step": 3630
2607
+ },
2608
+ {
2609
+ "epoch": 6.165572729197544,
2610
+ "grad_norm": 2.109375,
2611
+ "learning_rate": 2.7222900939242787e-06,
2612
+ "loss": 0.7932,
2613
+ "step": 3640
2614
+ },
2615
+ {
2616
+ "epoch": 6.182511115816219,
2617
+ "grad_norm": 2.203125,
2618
+ "learning_rate": 2.693079310786661e-06,
2619
+ "loss": 0.7611,
2620
+ "step": 3650
2621
+ },
2622
+ {
2623
+ "epoch": 6.199449502434893,
2624
+ "grad_norm": 2.1875,
2625
+ "learning_rate": 2.6639682188400017e-06,
2626
+ "loss": 0.7631,
2627
+ "step": 3660
2628
+ },
2629
+ {
2630
+ "epoch": 6.216387889053568,
2631
+ "grad_norm": 2.140625,
2632
+ "learning_rate": 2.6349580760900232e-06,
2633
+ "loss": 0.7784,
2634
+ "step": 3670
2635
+ },
2636
+ {
2637
+ "epoch": 6.233326275672242,
2638
+ "grad_norm": 2.234375,
2639
+ "learning_rate": 2.6060501361800333e-06,
2640
+ "loss": 0.7479,
2641
+ "step": 3680
2642
+ },
2643
+ {
2644
+ "epoch": 6.250264662290917,
2645
+ "grad_norm": 2.171875,
2646
+ "learning_rate": 2.57724564833675e-06,
2647
+ "loss": 0.7367,
2648
+ "step": 3690
2649
+ },
2650
+ {
2651
+ "epoch": 6.267203048909591,
2652
+ "grad_norm": 1.875,
2653
+ "learning_rate": 2.5485458573163114e-06,
2654
+ "loss": 0.7463,
2655
+ "step": 3700
2656
+ },
2657
+ {
2658
+ "epoch": 6.284141435528266,
2659
+ "grad_norm": 1.953125,
2660
+ "learning_rate": 2.519952003350499e-06,
2661
+ "loss": 0.7557,
2662
+ "step": 3710
2663
+ },
2664
+ {
2665
+ "epoch": 6.30107982214694,
2666
+ "grad_norm": 2.0,
2667
+ "learning_rate": 2.4914653220931283e-06,
2668
+ "loss": 0.8084,
2669
+ "step": 3720
2670
+ },
2671
+ {
2672
+ "epoch": 6.318018208765615,
2673
+ "grad_norm": 1.875,
2674
+ "learning_rate": 2.4630870445666576e-06,
2675
+ "loss": 0.7493,
2676
+ "step": 3730
2677
+ },
2678
+ {
2679
+ "epoch": 6.3349565953842895,
2680
+ "grad_norm": 2.15625,
2681
+ "learning_rate": 2.434818397108993e-06,
2682
+ "loss": 0.7959,
2683
+ "step": 3740
2684
+ },
2685
+ {
2686
+ "epoch": 6.351894982002964,
2687
+ "grad_norm": 2.21875,
2688
+ "learning_rate": 2.406660601320489e-06,
2689
+ "loss": 0.7245,
2690
+ "step": 3750
2691
+ },
2692
+ {
2693
+ "epoch": 6.3688333686216385,
2694
+ "grad_norm": 2.25,
2695
+ "learning_rate": 2.378614874011162e-06,
2696
+ "loss": 0.7637,
2697
+ "step": 3760
2698
+ },
2699
+ {
2700
+ "epoch": 6.385771755240313,
2701
+ "grad_norm": 2.15625,
2702
+ "learning_rate": 2.3506824271480987e-06,
2703
+ "loss": 0.7702,
2704
+ "step": 3770
2705
+ },
2706
+ {
2707
+ "epoch": 6.402710141858988,
2708
+ "grad_norm": 2.09375,
2709
+ "learning_rate": 2.322864467803097e-06,
2710
+ "loss": 0.7155,
2711
+ "step": 3780
2712
+ },
2713
+ {
2714
+ "epoch": 6.419648528477662,
2715
+ "grad_norm": 2.015625,
2716
+ "learning_rate": 2.2951621981004873e-06,
2717
+ "loss": 0.7925,
2718
+ "step": 3790
2719
+ },
2720
+ {
2721
+ "epoch": 6.436586915096337,
2722
+ "grad_norm": 1.96875,
2723
+ "learning_rate": 2.2675768151651993e-06,
2724
+ "loss": 0.7901,
2725
+ "step": 3800
2726
+ },
2727
+ {
2728
+ "epoch": 6.453525301715012,
2729
+ "grad_norm": 2.09375,
2730
+ "learning_rate": 2.240109511071014e-06,
2731
+ "loss": 0.729,
2732
+ "step": 3810
2733
+ },
2734
+ {
2735
+ "epoch": 6.470463688333687,
2736
+ "grad_norm": 2.109375,
2737
+ "learning_rate": 2.2127614727890627e-06,
2738
+ "loss": 0.7481,
2739
+ "step": 3820
2740
+ },
2741
+ {
2742
+ "epoch": 6.487402074952361,
2743
+ "grad_norm": 1.90625,
2744
+ "learning_rate": 2.1855338821365302e-06,
2745
+ "loss": 0.7148,
2746
+ "step": 3830
2747
+ },
2748
+ {
2749
+ "epoch": 6.504340461571036,
2750
+ "grad_norm": 1.8125,
2751
+ "learning_rate": 2.158427915725573e-06,
2752
+ "loss": 0.7748,
2753
+ "step": 3840
2754
+ },
2755
+ {
2756
+ "epoch": 6.52127884818971,
2757
+ "grad_norm": 2.125,
2758
+ "learning_rate": 2.131444744912492e-06,
2759
+ "loss": 0.7601,
2760
+ "step": 3850
2761
+ },
2762
+ {
2763
+ "epoch": 6.538217234808385,
2764
+ "grad_norm": 2.0625,
2765
+ "learning_rate": 2.1045855357470944e-06,
2766
+ "loss": 0.7397,
2767
+ "step": 3860
2768
+ },
2769
+ {
2770
+ "epoch": 6.555155621427059,
2771
+ "grad_norm": 2.578125,
2772
+ "learning_rate": 2.0778514489223207e-06,
2773
+ "loss": 0.7072,
2774
+ "step": 3870
2775
+ },
2776
+ {
2777
+ "epoch": 6.572094008045734,
2778
+ "grad_norm": 2.21875,
2779
+ "learning_rate": 2.051243639724071e-06,
2780
+ "loss": 0.7204,
2781
+ "step": 3880
2782
+ },
2783
+ {
2784
+ "epoch": 6.589032394664408,
2785
+ "grad_norm": 2.15625,
2786
+ "learning_rate": 2.024763257981296e-06,
2787
+ "loss": 0.7579,
2788
+ "step": 3890
2789
+ },
2790
+ {
2791
+ "epoch": 6.605970781283083,
2792
+ "grad_norm": 1.9765625,
2793
+ "learning_rate": 1.9984114480162976e-06,
2794
+ "loss": 0.7411,
2795
+ "step": 3900
2796
+ },
2797
+ {
2798
+ "epoch": 6.622909167901757,
2799
+ "grad_norm": 2.03125,
2800
+ "learning_rate": 1.9721893485952785e-06,
2801
+ "loss": 0.7513,
2802
+ "step": 3910
2803
+ },
2804
+ {
2805
+ "epoch": 6.639847554520432,
2806
+ "grad_norm": 2.0625,
2807
+ "learning_rate": 1.9460980928791407e-06,
2808
+ "loss": 0.7629,
2809
+ "step": 3920
2810
+ },
2811
+ {
2812
+ "epoch": 6.656785941139106,
2813
+ "grad_norm": 1.96875,
2814
+ "learning_rate": 1.9201388083745036e-06,
2815
+ "loss": 0.767,
2816
+ "step": 3930
2817
+ },
2818
+ {
2819
+ "epoch": 6.673724327757781,
2820
+ "grad_norm": 2.0625,
2821
+ "learning_rate": 1.8943126168849947e-06,
2822
+ "loss": 0.731,
2823
+ "step": 3940
2824
+ },
2825
+ {
2826
+ "epoch": 6.690662714376455,
2827
+ "grad_norm": 1.78125,
2828
+ "learning_rate": 1.868620634462756e-06,
2829
+ "loss": 0.7335,
2830
+ "step": 3950
2831
+ },
2832
+ {
2833
+ "epoch": 6.70760110099513,
2834
+ "grad_norm": 2.109375,
2835
+ "learning_rate": 1.8430639713602317e-06,
2836
+ "loss": 0.7791,
2837
+ "step": 3960
2838
+ },
2839
+ {
2840
+ "epoch": 6.7245394876138045,
2841
+ "grad_norm": 1.9921875,
2842
+ "learning_rate": 1.8176437319821789e-06,
2843
+ "loss": 0.7231,
2844
+ "step": 3970
2845
+ },
2846
+ {
2847
+ "epoch": 6.741477874232479,
2848
+ "grad_norm": 1.9375,
2849
+ "learning_rate": 1.79236101483794e-06,
2850
+ "loss": 0.7355,
2851
+ "step": 3980
2852
+ },
2853
+ {
2854
+ "epoch": 6.7584162608511535,
2855
+ "grad_norm": 1.734375,
2856
+ "learning_rate": 1.7672169124939843e-06,
2857
+ "loss": 0.7737,
2858
+ "step": 3990
2859
+ },
2860
+ {
2861
+ "epoch": 6.775354647469829,
2862
+ "grad_norm": 1.96875,
2863
+ "learning_rate": 1.7422125115266785e-06,
2864
+ "loss": 0.7269,
2865
+ "step": 4000
2866
+ },
2867
+ {
2868
+ "epoch": 6.775354647469829,
2869
+ "eval_loss": 1.0812190771102905,
2870
+ "eval_runtime": 21.7625,
2871
+ "eval_samples_per_second": 24.124,
2872
+ "eval_steps_per_second": 24.124,
2873
+ "step": 4000
2874
+ },
2875
+ {
2876
+ "epoch": 6.7922930340885035,
2877
+ "grad_norm": 1.7890625,
2878
+ "learning_rate": 1.7173488924753451e-06,
2879
+ "loss": 0.7756,
2880
+ "step": 4010
2881
+ },
2882
+ {
2883
+ "epoch": 6.809231420707178,
2884
+ "grad_norm": 1.6953125,
2885
+ "learning_rate": 1.6926271297955549e-06,
2886
+ "loss": 0.7597,
2887
+ "step": 4020
2888
+ },
2889
+ {
2890
+ "epoch": 6.8261698073258525,
2891
+ "grad_norm": 1.90625,
2892
+ "learning_rate": 1.668048291812709e-06,
2893
+ "loss": 0.7463,
2894
+ "step": 4030
2895
+ },
2896
+ {
2897
+ "epoch": 6.843108193944527,
2898
+ "grad_norm": 3.25,
2899
+ "learning_rate": 1.6436134406758635e-06,
2900
+ "loss": 0.7202,
2901
+ "step": 4040
2902
+ },
2903
+ {
2904
+ "epoch": 6.860046580563202,
2905
+ "grad_norm": 1.6875,
2906
+ "learning_rate": 1.6193236323118283e-06,
2907
+ "loss": 0.7765,
2908
+ "step": 4050
2909
+ },
2910
+ {
2911
+ "epoch": 6.876984967181876,
2912
+ "grad_norm": 1.84375,
2913
+ "learning_rate": 1.5951799163795461e-06,
2914
+ "loss": 0.7552,
2915
+ "step": 4060
2916
+ },
2917
+ {
2918
+ "epoch": 6.893923353800551,
2919
+ "grad_norm": 1.6484375,
2920
+ "learning_rate": 1.5711833362247204e-06,
2921
+ "loss": 0.7565,
2922
+ "step": 4070
2923
+ },
2924
+ {
2925
+ "epoch": 6.910861740419225,
2926
+ "grad_norm": 1.7265625,
2927
+ "learning_rate": 1.547334928834739e-06,
2928
+ "loss": 0.7342,
2929
+ "step": 4080
2930
+ },
2931
+ {
2932
+ "epoch": 6.9278001270379,
2933
+ "grad_norm": 1.578125,
2934
+ "learning_rate": 1.523635724793852e-06,
2935
+ "loss": 0.7602,
2936
+ "step": 4090
2937
+ },
2938
+ {
2939
+ "epoch": 6.944738513656574,
2940
+ "grad_norm": 1.6015625,
2941
+ "learning_rate": 1.5000867482386478e-06,
2942
+ "loss": 0.7839,
2943
+ "step": 4100
2944
+ },
2945
+ {
2946
+ "epoch": 6.961676900275249,
2947
+ "grad_norm": 1.6171875,
2948
+ "learning_rate": 1.4766890168137816e-06,
2949
+ "loss": 0.7512,
2950
+ "step": 4110
2951
+ },
2952
+ {
2953
+ "epoch": 6.978615286893923,
2954
+ "grad_norm": 1.6484375,
2955
+ "learning_rate": 1.4534435416280135e-06,
2956
+ "loss": 0.7715,
2957
+ "step": 4120
2958
+ },
2959
+ {
2960
+ "epoch": 6.995553673512598,
2961
+ "grad_norm": 1.546875,
2962
+ "learning_rate": 1.4303513272105057e-06,
2963
+ "loss": 0.7924,
2964
+ "step": 4130
2965
+ },
2966
+ {
2967
+ "epoch": 7.012492060131272,
2968
+ "grad_norm": 1.4453125,
2969
+ "learning_rate": 1.4074133714674116e-06,
2970
+ "loss": 0.7509,
2971
+ "step": 4140
2972
+ },
2973
+ {
2974
+ "epoch": 7.029430446749947,
2975
+ "grad_norm": 1.3984375,
2976
+ "learning_rate": 1.3846306656387603e-06,
2977
+ "loss": 0.7349,
2978
+ "step": 4150
2979
+ },
2980
+ {
2981
+ "epoch": 7.046368833368621,
2982
+ "grad_norm": 1.4765625,
2983
+ "learning_rate": 1.3620041942556127e-06,
2984
+ "loss": 0.7525,
2985
+ "step": 4160
2986
+ },
2987
+ {
2988
+ "epoch": 7.063307219987296,
2989
+ "grad_norm": 1.34375,
2990
+ "learning_rate": 1.339534935097524e-06,
2991
+ "loss": 0.7515,
2992
+ "step": 4170
2993
+ },
2994
+ {
2995
+ "epoch": 7.0802456066059705,
2996
+ "grad_norm": 1.4296875,
2997
+ "learning_rate": 1.3172238591502794e-06,
2998
+ "loss": 0.7433,
2999
+ "step": 4180
3000
+ },
3001
+ {
3002
+ "epoch": 7.097183993224645,
3003
+ "grad_norm": 1.265625,
3004
+ "learning_rate": 1.2950719305639464e-06,
3005
+ "loss": 0.7416,
3006
+ "step": 4190
3007
+ },
3008
+ {
3009
+ "epoch": 7.1141223798433195,
3010
+ "grad_norm": 1.3984375,
3011
+ "learning_rate": 1.2730801066112024e-06,
3012
+ "loss": 0.7115,
3013
+ "step": 4200
3014
+ },
3015
+ {
3016
+ "epoch": 7.131060766461994,
3017
+ "grad_norm": 1.3203125,
3018
+ "learning_rate": 1.251249337645965e-06,
3019
+ "loss": 0.6892,
3020
+ "step": 4210
3021
+ },
3022
+ {
3023
+ "epoch": 7.1479991530806695,
3024
+ "grad_norm": 1.3125,
3025
+ "learning_rate": 1.229580567062334e-06,
3026
+ "loss": 0.704,
3027
+ "step": 4220
3028
+ },
3029
+ {
3030
+ "epoch": 7.164937539699344,
3031
+ "grad_norm": 1.3203125,
3032
+ "learning_rate": 1.2080747312538082e-06,
3033
+ "loss": 0.7021,
3034
+ "step": 4230
3035
+ },
3036
+ {
3037
+ "epoch": 7.1818759263180185,
3038
+ "grad_norm": 1.3828125,
3039
+ "learning_rate": 1.1867327595728373e-06,
3040
+ "loss": 0.6669,
3041
+ "step": 4240
3042
+ },
3043
+ {
3044
+ "epoch": 7.198814312936693,
3045
+ "grad_norm": 1.2890625,
3046
+ "learning_rate": 1.1655555742906438e-06,
3047
+ "loss": 0.7433,
3048
+ "step": 4250
3049
+ },
3050
+ {
3051
+ "epoch": 7.215752699555368,
3052
+ "grad_norm": 1.3046875,
3053
+ "learning_rate": 1.1445440905573857e-06,
3054
+ "loss": 0.7294,
3055
+ "step": 4260
3056
+ },
3057
+ {
3058
+ "epoch": 7.232691086174042,
3059
+ "grad_norm": 1.359375,
3060
+ "learning_rate": 1.1236992163625933e-06,
3061
+ "loss": 0.7121,
3062
+ "step": 4270
3063
+ },
3064
+ {
3065
+ "epoch": 7.249629472792717,
3066
+ "grad_norm": 1.3046875,
3067
+ "learning_rate": 1.1030218524959375e-06,
3068
+ "loss": 0.6407,
3069
+ "step": 4280
3070
+ },
3071
+ {
3072
+ "epoch": 7.266567859411391,
3073
+ "grad_norm": 1.515625,
3074
+ "learning_rate": 1.082512892508309e-06,
3075
+ "loss": 0.7426,
3076
+ "step": 4290
3077
+ },
3078
+ {
3079
+ "epoch": 7.283506246030066,
3080
+ "grad_norm": 1.265625,
3081
+ "learning_rate": 1.062173222673194e-06,
3082
+ "loss": 0.7256,
3083
+ "step": 4300
3084
+ },
3085
+ {
3086
+ "epoch": 7.30044463264874,
3087
+ "grad_norm": 1.140625,
3088
+ "learning_rate": 1.0420037219483842e-06,
3089
+ "loss": 0.7149,
3090
+ "step": 4310
3091
+ },
3092
+ {
3093
+ "epoch": 7.317383019267415,
3094
+ "grad_norm": 1.171875,
3095
+ "learning_rate": 1.0220052619379844e-06,
3096
+ "loss": 0.7327,
3097
+ "step": 4320
3098
+ },
3099
+ {
3100
+ "epoch": 7.334321405886089,
3101
+ "grad_norm": 1.2734375,
3102
+ "learning_rate": 1.0021787068547568e-06,
3103
+ "loss": 0.7728,
3104
+ "step": 4330
3105
+ },
3106
+ {
3107
+ "epoch": 7.351259792504764,
3108
+ "grad_norm": 1.2890625,
3109
+ "learning_rate": 9.825249134827664e-07,
3110
+ "loss": 0.745,
3111
+ "step": 4340
3112
+ },
3113
+ {
3114
+ "epoch": 7.368198179123438,
3115
+ "grad_norm": 1.046875,
3116
+ "learning_rate": 9.630447311403623e-07,
3117
+ "loss": 0.7625,
3118
+ "step": 4350
3119
+ },
3120
+ {
3121
+ "epoch": 7.385136565742113,
3122
+ "grad_norm": 1.0703125,
3123
+ "learning_rate": 9.437390016434711e-07,
3124
+ "loss": 0.7297,
3125
+ "step": 4360
3126
+ },
3127
+ {
3128
+ "epoch": 7.402074952360787,
3129
+ "grad_norm": 1.1015625,
3130
+ "learning_rate": 9.246085592692183e-07,
3131
+ "loss": 0.6938,
3132
+ "step": 4370
3133
+ },
3134
+ {
3135
+ "epoch": 7.419013338979462,
3136
+ "grad_norm": 1.1015625,
3137
+ "learning_rate": 9.056542307198823e-07,
3138
+ "loss": 0.721,
3139
+ "step": 4380
3140
+ },
3141
+ {
3142
+ "epoch": 7.435951725598136,
3143
+ "grad_norm": 1.0703125,
3144
+ "learning_rate": 8.868768350871592e-07,
3145
+ "loss": 0.712,
3146
+ "step": 4390
3147
+ },
3148
+ {
3149
+ "epoch": 7.452890112216811,
3150
+ "grad_norm": 1.1640625,
3151
+ "learning_rate": 8.682771838167775e-07,
3152
+ "loss": 0.7684,
3153
+ "step": 4400
3154
+ },
3155
+ {
3156
+ "epoch": 7.469828498835486,
3157
+ "grad_norm": 1.109375,
3158
+ "learning_rate": 8.49856080673423e-07,
3159
+ "loss": 0.723,
3160
+ "step": 4410
3161
+ },
3162
+ {
3163
+ "epoch": 7.486766885454161,
3164
+ "grad_norm": 1.046875,
3165
+ "learning_rate": 8.316143217060129e-07,
3166
+ "loss": 0.7165,
3167
+ "step": 4420
3168
+ },
3169
+ {
3170
+ "epoch": 7.503705272072835,
3171
+ "grad_norm": 1.0625,
3172
+ "learning_rate": 8.135526952132877e-07,
3173
+ "loss": 0.7471,
3174
+ "step": 4430
3175
+ },
3176
+ {
3177
+ "epoch": 7.52064365869151,
3178
+ "grad_norm": 1.109375,
3179
+ "learning_rate": 7.956719817097491e-07,
3180
+ "loss": 0.7388,
3181
+ "step": 4440
3182
+ },
3183
+ {
3184
+ "epoch": 7.5375820453101845,
3185
+ "grad_norm": 1.0078125,
3186
+ "learning_rate": 7.779729538919351e-07,
3187
+ "loss": 0.7165,
3188
+ "step": 4450
3189
+ },
3190
+ {
3191
+ "epoch": 7.554520431928859,
3192
+ "grad_norm": 0.9609375,
3193
+ "learning_rate": 7.6045637660502e-07,
3194
+ "loss": 0.7349,
3195
+ "step": 4460
3196
+ },
3197
+ {
3198
+ "epoch": 7.5714588185475336,
3199
+ "grad_norm": 1.171875,
3200
+ "learning_rate": 7.4312300680977e-07,
3201
+ "loss": 0.6813,
3202
+ "step": 4470
3203
+ },
3204
+ {
3205
+ "epoch": 7.588397205166208,
3206
+ "grad_norm": 1.09375,
3207
+ "learning_rate": 7.259735935498297e-07,
3208
+ "loss": 0.7447,
3209
+ "step": 4480
3210
+ },
3211
+ {
3212
+ "epoch": 7.605335591784883,
3213
+ "grad_norm": 0.9609375,
3214
+ "learning_rate": 7.090088779193516e-07,
3215
+ "loss": 0.6976,
3216
+ "step": 4490
3217
+ },
3218
+ {
3219
+ "epoch": 7.622273978403557,
3220
+ "grad_norm": 0.98046875,
3221
+ "learning_rate": 6.922295930309691e-07,
3222
+ "loss": 0.7372,
3223
+ "step": 4500
3224
+ },
3225
+ {
3226
+ "epoch": 7.622273978403557,
3227
+ "eval_loss": 1.0816632509231567,
3228
+ "eval_runtime": 21.0317,
3229
+ "eval_samples_per_second": 24.962,
3230
+ "eval_steps_per_second": 24.962,
3231
+ "step": 4500
3232
+ },
3233
+ {
3234
+ "epoch": 7.639212365022232,
3235
+ "grad_norm": 1.078125,
3236
+ "learning_rate": 6.756364639841217e-07,
3237
+ "loss": 0.703,
3238
+ "step": 4510
3239
+ },
3240
+ {
3241
+ "epoch": 7.656150751640906,
3242
+ "grad_norm": 1.0390625,
3243
+ "learning_rate": 6.592302078337132e-07,
3244
+ "loss": 0.7121,
3245
+ "step": 4520
3246
+ },
3247
+ {
3248
+ "epoch": 7.673089138259581,
3249
+ "grad_norm": 1.0078125,
3250
+ "learning_rate": 6.430115335591291e-07,
3251
+ "loss": 0.7669,
3252
+ "step": 4530
3253
+ },
3254
+ {
3255
+ "epoch": 7.690027524878255,
3256
+ "grad_norm": 1.0234375,
3257
+ "learning_rate": 6.26981142033602e-07,
3258
+ "loss": 0.7015,
3259
+ "step": 4540
3260
+ },
3261
+ {
3262
+ "epoch": 7.70696591149693,
3263
+ "grad_norm": 1.0390625,
3264
+ "learning_rate": 6.111397259939128e-07,
3265
+ "loss": 0.736,
3266
+ "step": 4550
3267
+ },
3268
+ {
3269
+ "epoch": 7.723904298115604,
3270
+ "grad_norm": 1.0390625,
3271
+ "learning_rate": 5.954879700104732e-07,
3272
+ "loss": 0.7379,
3273
+ "step": 4560
3274
+ },
3275
+ {
3276
+ "epoch": 7.740842684734279,
3277
+ "grad_norm": 1.09375,
3278
+ "learning_rate": 5.800265504577202e-07,
3279
+ "loss": 0.7687,
3280
+ "step": 4570
3281
+ },
3282
+ {
3283
+ "epoch": 7.757781071352953,
3284
+ "grad_norm": 0.96875,
3285
+ "learning_rate": 5.647561354849079e-07,
3286
+ "loss": 0.7316,
3287
+ "step": 4580
3288
+ },
3289
+ {
3290
+ "epoch": 7.774719457971628,
3291
+ "grad_norm": 1.03125,
3292
+ "learning_rate": 5.496773849872183e-07,
3293
+ "loss": 0.7466,
3294
+ "step": 4590
3295
+ },
3296
+ {
3297
+ "epoch": 7.791657844590302,
3298
+ "grad_norm": 1.09375,
3299
+ "learning_rate": 5.347909505772569e-07,
3300
+ "loss": 0.734,
3301
+ "step": 4600
3302
+ },
3303
+ {
3304
+ "epoch": 7.808596231208977,
3305
+ "grad_norm": 1.0546875,
3306
+ "learning_rate": 5.200974755568849e-07,
3307
+ "loss": 0.7497,
3308
+ "step": 4610
3309
+ },
3310
+ {
3311
+ "epoch": 7.8255346178276515,
3312
+ "grad_norm": 1.046875,
3313
+ "learning_rate": 5.055975948894226e-07,
3314
+ "loss": 0.7562,
3315
+ "step": 4620
3316
+ },
3317
+ {
3318
+ "epoch": 7.842473004446326,
3319
+ "grad_norm": 1.125,
3320
+ "learning_rate": 4.912919351722151e-07,
3321
+ "loss": 0.7017,
3322
+ "step": 4630
3323
+ },
3324
+ {
3325
+ "epoch": 7.859411391065001,
3326
+ "grad_norm": 1.1328125,
3327
+ "learning_rate": 4.771811146095451e-07,
3328
+ "loss": 0.6976,
3329
+ "step": 4640
3330
+ },
3331
+ {
3332
+ "epoch": 7.876349777683676,
3333
+ "grad_norm": 1.046875,
3334
+ "learning_rate": 4.6326574298592666e-07,
3335
+ "loss": 0.6964,
3336
+ "step": 4650
3337
+ },
3338
+ {
3339
+ "epoch": 7.8932881643023505,
3340
+ "grad_norm": 1.203125,
3341
+ "learning_rate": 4.49546421639746e-07,
3342
+ "loss": 0.7239,
3343
+ "step": 4660
3344
+ },
3345
+ {
3346
+ "epoch": 7.910226550921025,
3347
+ "grad_norm": 1.0625,
3348
+ "learning_rate": 4.360237434372838e-07,
3349
+ "loss": 0.7632,
3350
+ "step": 4670
3351
+ },
3352
+ {
3353
+ "epoch": 7.9271649375396995,
3354
+ "grad_norm": 1.1640625,
3355
+ "learning_rate": 4.226982927470874e-07,
3356
+ "loss": 0.7184,
3357
+ "step": 4680
3358
+ },
3359
+ {
3360
+ "epoch": 7.944103324158374,
3361
+ "grad_norm": 1.1484375,
3362
+ "learning_rate": 4.0957064541472305e-07,
3363
+ "loss": 0.7238,
3364
+ "step": 4690
3365
+ },
3366
+ {
3367
+ "epoch": 7.961041710777049,
3368
+ "grad_norm": 1.421875,
3369
+ "learning_rate": 3.966413687378895e-07,
3370
+ "loss": 0.7361,
3371
+ "step": 4700
3372
+ },
3373
+ {
3374
+ "epoch": 7.977980097395723,
3375
+ "grad_norm": 1.390625,
3376
+ "learning_rate": 3.8391102144190175e-07,
3377
+ "loss": 0.723,
3378
+ "step": 4710
3379
+ },
3380
+ {
3381
+ "epoch": 7.994918484014398,
3382
+ "grad_norm": 1.4296875,
3383
+ "learning_rate": 3.7138015365554834e-07,
3384
+ "loss": 0.7064,
3385
+ "step": 4720
3386
+ },
3387
+ {
3388
+ "epoch": 8.011856870633073,
3389
+ "grad_norm": 1.3125,
3390
+ "learning_rate": 3.590493068873163e-07,
3391
+ "loss": 0.7317,
3392
+ "step": 4730
3393
+ },
3394
+ {
3395
+ "epoch": 8.028795257251748,
3396
+ "grad_norm": 1.3359375,
3397
+ "learning_rate": 3.4691901400199234e-07,
3398
+ "loss": 0.7102,
3399
+ "step": 4740
3400
+ },
3401
+ {
3402
+ "epoch": 8.045733643870422,
3403
+ "grad_norm": 2.4375,
3404
+ "learning_rate": 3.349897991976336e-07,
3405
+ "loss": 0.681,
3406
+ "step": 4750
3407
+ },
3408
+ {
3409
+ "epoch": 8.062672030489097,
3410
+ "grad_norm": 2.171875,
3411
+ "learning_rate": 3.232621779829176e-07,
3412
+ "loss": 0.6939,
3413
+ "step": 4760
3414
+ },
3415
+ {
3416
+ "epoch": 8.079610417107771,
3417
+ "grad_norm": 2.140625,
3418
+ "learning_rate": 3.1173665715486076e-07,
3419
+ "loss": 0.7276,
3420
+ "step": 4770
3421
+ },
3422
+ {
3423
+ "epoch": 8.096548803726446,
3424
+ "grad_norm": 2.09375,
3425
+ "learning_rate": 3.0041373477692315e-07,
3426
+ "loss": 0.6762,
3427
+ "step": 4780
3428
+ },
3429
+ {
3430
+ "epoch": 8.11348719034512,
3431
+ "grad_norm": 2.171875,
3432
+ "learning_rate": 2.8929390015748124e-07,
3433
+ "loss": 0.7547,
3434
+ "step": 4790
3435
+ },
3436
+ {
3437
+ "epoch": 8.130425576963795,
3438
+ "grad_norm": 3.71875,
3439
+ "learning_rate": 2.7837763382868253e-07,
3440
+ "loss": 0.716,
3441
+ "step": 4800
3442
+ },
3443
+ {
3444
+ "epoch": 8.14736396358247,
3445
+ "grad_norm": 3.15625,
3446
+ "learning_rate": 2.6766540752568514e-07,
3447
+ "loss": 0.7306,
3448
+ "step": 4810
3449
+ },
3450
+ {
3451
+ "epoch": 8.164302350201144,
3452
+ "grad_norm": 3.46875,
3453
+ "learning_rate": 2.5715768416626486e-07,
3454
+ "loss": 0.6856,
3455
+ "step": 4820
3456
+ },
3457
+ {
3458
+ "epoch": 8.181240736819818,
3459
+ "grad_norm": 3.859375,
3460
+ "learning_rate": 2.4685491783081715e-07,
3461
+ "loss": 0.6798,
3462
+ "step": 4830
3463
+ },
3464
+ {
3465
+ "epoch": 8.198179123438493,
3466
+ "grad_norm": 3.46875,
3467
+ "learning_rate": 2.3675755374272857e-07,
3468
+ "loss": 0.7652,
3469
+ "step": 4840
3470
+ },
3471
+ {
3472
+ "epoch": 8.215117510057167,
3473
+ "grad_norm": 8.0,
3474
+ "learning_rate": 2.268660282491436e-07,
3475
+ "loss": 0.6881,
3476
+ "step": 4850
3477
+ },
3478
+ {
3479
+ "epoch": 8.232055896675842,
3480
+ "grad_norm": 7.21875,
3481
+ "learning_rate": 2.1718076880210325e-07,
3482
+ "loss": 0.7532,
3483
+ "step": 4860
3484
+ },
3485
+ {
3486
+ "epoch": 8.248994283294516,
3487
+ "grad_norm": 7.0625,
3488
+ "learning_rate": 2.0770219394007362e-07,
3489
+ "loss": 0.6872,
3490
+ "step": 4870
3491
+ },
3492
+ {
3493
+ "epoch": 8.265932669913191,
3494
+ "grad_norm": 7.8125,
3495
+ "learning_rate": 1.9843071326986264e-07,
3496
+ "loss": 0.7416,
3497
+ "step": 4880
3498
+ },
3499
+ {
3500
+ "epoch": 8.282871056531866,
3501
+ "grad_norm": 8.3125,
3502
+ "learning_rate": 1.893667274489136e-07,
3503
+ "loss": 0.703,
3504
+ "step": 4890
3505
+ },
3506
+ {
3507
+ "epoch": 8.29980944315054,
3508
+ "grad_norm": 2.34375,
3509
+ "learning_rate": 1.8051062816799913e-07,
3510
+ "loss": 0.6915,
3511
+ "step": 4900
3512
+ },
3513
+ {
3514
+ "epoch": 8.316747829769215,
3515
+ "grad_norm": 2.109375,
3516
+ "learning_rate": 1.7186279813428518e-07,
3517
+ "loss": 0.6801,
3518
+ "step": 4910
3519
+ },
3520
+ {
3521
+ "epoch": 8.333686216387889,
3522
+ "grad_norm": 2.03125,
3523
+ "learning_rate": 1.6342361105480098e-07,
3524
+ "loss": 0.7441,
3525
+ "step": 4920
3526
+ },
3527
+ {
3528
+ "epoch": 8.350624603006564,
3529
+ "grad_norm": 2.140625,
3530
+ "learning_rate": 1.551934316202869e-07,
3531
+ "loss": 0.7246,
3532
+ "step": 4930
3533
+ },
3534
+ {
3535
+ "epoch": 8.367562989625238,
3536
+ "grad_norm": 2.140625,
3537
+ "learning_rate": 1.471726154894304e-07,
3538
+ "loss": 0.6718,
3539
+ "step": 4940
3540
+ },
3541
+ {
3542
+ "epoch": 8.384501376243913,
3543
+ "grad_norm": 1.65625,
3544
+ "learning_rate": 1.39361509273504e-07,
3545
+ "loss": 0.709,
3546
+ "step": 4950
3547
+ },
3548
+ {
3549
+ "epoch": 8.401439762862587,
3550
+ "grad_norm": 1.875,
3551
+ "learning_rate": 1.3176045052138097e-07,
3552
+ "loss": 0.7661,
3553
+ "step": 4960
3554
+ },
3555
+ {
3556
+ "epoch": 8.418378149481262,
3557
+ "grad_norm": 2.359375,
3558
+ "learning_rate": 1.2436976770495267e-07,
3559
+ "loss": 0.7727,
3560
+ "step": 4970
3561
+ },
3562
+ {
3563
+ "epoch": 8.435316536099936,
3564
+ "grad_norm": 1.703125,
3565
+ "learning_rate": 1.1718978020492988e-07,
3566
+ "loss": 0.802,
3567
+ "step": 4980
3568
+ },
3569
+ {
3570
+ "epoch": 8.45225492271861,
3571
+ "grad_norm": 1.8046875,
3572
+ "learning_rate": 1.1022079829704436e-07,
3573
+ "loss": 0.7435,
3574
+ "step": 4990
3575
+ },
3576
+ {
3577
+ "epoch": 8.469193309337285,
3578
+ "grad_norm": 1.703125,
3579
+ "learning_rate": 1.0346312313864127e-07,
3580
+ "loss": 0.7366,
3581
+ "step": 5000
3582
+ },
3583
+ {
3584
+ "epoch": 8.469193309337285,
3585
+ "eval_loss": 1.0841984748840332,
3586
+ "eval_runtime": 21.0727,
3587
+ "eval_samples_per_second": 24.914,
3588
+ "eval_steps_per_second": 24.914,
3589
+ "step": 5000
3590
+ },
3591
+ {
3592
+ "epoch": 8.48613169595596,
3593
+ "grad_norm": 2.265625,
3594
+ "learning_rate": 9.691704675565904e-08,
3595
+ "loss": 0.7348,
3596
+ "step": 5010
3597
+ },
3598
+ {
3599
+ "epoch": 8.503070082574634,
3600
+ "grad_norm": 1.953125,
3601
+ "learning_rate": 9.058285203001837e-08,
3602
+ "loss": 0.703,
3603
+ "step": 5020
3604
+ },
3605
+ {
3606
+ "epoch": 8.520008469193309,
3607
+ "grad_norm": 1.796875,
3608
+ "learning_rate": 8.446081268738971e-08,
3609
+ "loss": 0.6796,
3610
+ "step": 5030
3611
+ },
3612
+ {
3613
+ "epoch": 8.536946855811983,
3614
+ "grad_norm": 1.9140625,
3615
+ "learning_rate": 7.855119328537109e-08,
3616
+ "loss": 0.7424,
3617
+ "step": 5040
3618
+ },
3619
+ {
3620
+ "epoch": 8.553885242430658,
3621
+ "grad_norm": 1.7890625,
3622
+ "learning_rate": 7.285424920204953e-08,
3623
+ "loss": 0.7379,
3624
+ "step": 5050
3625
+ },
3626
+ {
3627
+ "epoch": 8.570823629049332,
3628
+ "grad_norm": 1.90625,
3629
+ "learning_rate": 6.737022662497095e-08,
3630
+ "loss": 0.7113,
3631
+ "step": 5060
3632
+ },
3633
+ {
3634
+ "epoch": 8.587762015668007,
3635
+ "grad_norm": 1.9140625,
3636
+ "learning_rate": 6.209936254049808e-08,
3637
+ "loss": 0.698,
3638
+ "step": 5070
3639
+ },
3640
+ {
3641
+ "epoch": 8.604700402286682,
3642
+ "grad_norm": 2.25,
3643
+ "learning_rate": 5.704188472356764e-08,
3644
+ "loss": 0.7441,
3645
+ "step": 5080
3646
+ },
3647
+ {
3648
+ "epoch": 8.621638788905356,
3649
+ "grad_norm": 2.375,
3650
+ "learning_rate": 5.219801172785255e-08,
3651
+ "loss": 0.6628,
3652
+ "step": 5090
3653
+ },
3654
+ {
3655
+ "epoch": 8.63857717552403,
3656
+ "grad_norm": 2.09375,
3657
+ "learning_rate": 4.756795287631288e-08,
3658
+ "loss": 0.7012,
3659
+ "step": 5100
3660
+ },
3661
+ {
3662
+ "epoch": 8.655515562142705,
3663
+ "grad_norm": 2.375,
3664
+ "learning_rate": 4.315190825215143e-08,
3665
+ "loss": 0.7372,
3666
+ "step": 5110
3667
+ },
3668
+ {
3669
+ "epoch": 8.67245394876138,
3670
+ "grad_norm": 1.8125,
3671
+ "learning_rate": 3.895006869016837e-08,
3672
+ "loss": 0.7353,
3673
+ "step": 5120
3674
+ },
3675
+ {
3676
+ "epoch": 8.689392335380056,
3677
+ "grad_norm": 1.6484375,
3678
+ "learning_rate": 3.496261576851345e-08,
3679
+ "loss": 0.7127,
3680
+ "step": 5130
3681
+ },
3682
+ {
3683
+ "epoch": 8.706330721998729,
3684
+ "grad_norm": 2.15625,
3685
+ "learning_rate": 3.1189721800839453e-08,
3686
+ "loss": 0.7462,
3687
+ "step": 5140
3688
+ },
3689
+ {
3690
+ "epoch": 8.723269108617405,
3691
+ "grad_norm": 2.140625,
3692
+ "learning_rate": 2.763154982885541e-08,
3693
+ "loss": 0.7486,
3694
+ "step": 5150
3695
+ },
3696
+ {
3697
+ "epoch": 8.74020749523608,
3698
+ "grad_norm": 1.9296875,
3699
+ "learning_rate": 2.4288253615282754e-08,
3700
+ "loss": 0.7136,
3701
+ "step": 5160
3702
+ },
3703
+ {
3704
+ "epoch": 8.757145881854754,
3705
+ "grad_norm": 2.046875,
3706
+ "learning_rate": 2.1159977637208452e-08,
3707
+ "loss": 0.746,
3708
+ "step": 5170
3709
+ },
3710
+ {
3711
+ "epoch": 8.774084268473429,
3712
+ "grad_norm": 1.90625,
3713
+ "learning_rate": 1.824685707984164e-08,
3714
+ "loss": 0.7379,
3715
+ "step": 5180
3716
+ },
3717
+ {
3718
+ "epoch": 8.791022655092103,
3719
+ "grad_norm": 1.9375,
3720
+ "learning_rate": 1.5549017830674416e-08,
3721
+ "loss": 0.7561,
3722
+ "step": 5190
3723
+ },
3724
+ {
3725
+ "epoch": 8.807961041710778,
3726
+ "grad_norm": 1.96875,
3727
+ "learning_rate": 1.3066576474038416e-08,
3728
+ "loss": 0.7722,
3729
+ "step": 5200
3730
+ },
3731
+ {
3732
+ "epoch": 8.824899428329452,
3733
+ "grad_norm": 2.03125,
3734
+ "learning_rate": 1.0799640286068836e-08,
3735
+ "loss": 0.7318,
3736
+ "step": 5210
3737
+ },
3738
+ {
3739
+ "epoch": 8.841837814948127,
3740
+ "grad_norm": 1.7890625,
3741
+ "learning_rate": 8.748307230067587e-09,
3742
+ "loss": 0.7358,
3743
+ "step": 5220
3744
+ },
3745
+ {
3746
+ "epoch": 8.858776201566801,
3747
+ "grad_norm": 1.7734375,
3748
+ "learning_rate": 6.912665952270581e-09,
3749
+ "loss": 0.7051,
3750
+ "step": 5230
3751
+ },
3752
+ {
3753
+ "epoch": 8.875714588185476,
3754
+ "grad_norm": 1.8203125,
3755
+ "learning_rate": 5.29279577801689e-09,
3756
+ "loss": 0.7542,
3757
+ "step": 5240
3758
+ },
3759
+ {
3760
+ "epoch": 8.89265297480415,
3761
+ "grad_norm": 2.0625,
3762
+ "learning_rate": 3.888766708319836e-09,
3763
+ "loss": 0.7354,
3764
+ "step": 5250
3765
+ },
3766
+ {
3767
+ "epoch": 8.909591361422825,
3768
+ "grad_norm": 2.1875,
3769
+ "learning_rate": 2.700639416843287e-09,
3770
+ "loss": 0.7226,
3771
+ "step": 5260
3772
+ },
3773
+ {
3774
+ "epoch": 8.9265297480415,
3775
+ "grad_norm": 2.171875,
3776
+ "learning_rate": 1.7284652472787655e-09,
3777
+ "loss": 0.7387,
3778
+ "step": 5270
3779
+ },
3780
+ {
3781
+ "epoch": 8.943468134660174,
3782
+ "grad_norm": 2.125,
3783
+ "learning_rate": 9.722862111277708e-10,
3784
+ "loss": 0.6839,
3785
+ "step": 5280
3786
+ },
3787
+ {
3788
+ "epoch": 8.960406521278848,
3789
+ "grad_norm": 2.34375,
3790
+ "learning_rate": 4.321349858843471e-10,
3791
+ "loss": 0.7071,
3792
+ "step": 5290
3793
+ },
3794
+ {
3795
+ "epoch": 8.977344907897523,
3796
+ "grad_norm": 1.9765625,
3797
+ "learning_rate": 1.080349136250991e-10,
3798
+ "loss": 0.7484,
3799
+ "step": 5300
3800
+ },
3801
+ {
3802
+ "epoch": 8.994283294516197,
3803
+ "grad_norm": 1.9375,
3804
+ "learning_rate": 0.0,
3805
+ "loss": 0.7226,
3806
+ "step": 5310
3807
+ }
3808
+ ],
3809
+ "logging_steps": 10,
3810
+ "max_steps": 5310,
3811
+ "num_input_tokens_seen": 0,
3812
+ "num_train_epochs": 9,
3813
+ "save_steps": 0,
3814
+ "stateful_callbacks": {
3815
+ "TrainerControl": {
3816
+ "args": {
3817
+ "should_epoch_stop": false,
3818
+ "should_evaluate": false,
3819
+ "should_log": false,
3820
+ "should_save": true,
3821
+ "should_training_stop": true
3822
+ },
3823
+ "attributes": {}
3824
+ }
3825
+ },
3826
+ "total_flos": 5.095460800932741e+17,
3827
+ "train_batch_size": 1,
3828
+ "trial_name": null,
3829
+ "trial_params": null
3830
+ }
checkpoint-5310/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe6f6e1a55b6ce6e9636cb2316a96482aeec5c5fc5be4262f061ad26b88ececb
3
+ size 5304
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "NousResearch/Meta-Llama-3-8B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128009,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 8,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 500000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.44.2",
27
+ "use_cache": false,
28
+ "vocab_size": 128256
29
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 8.994283294516197,
3
+ "eval_loss": 1.0843082666397095,
4
+ "eval_runtime": 21.0991,
5
+ "eval_samples_per_second": 24.883,
6
+ "eval_steps_per_second": 24.883
7
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128009
7
+ ],
8
+ "max_length": 4096,
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.44.2"
12
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e2b3bba182357967751ba25b34ef5149858fc5321b1a326066589aed1a3a882
3
+ size 4976698672
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe8e803e15da12b9b2227fcd2e14ebdf6b5cfe3fcc8c947863eaef8c200a2d7c
3
+ size 4999802720
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eb88d196a15aac180b8437683b358ebd28ef8599ce887f8960f54e6defb21f3
3
+ size 4915916176
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f41e6f9a7ea6b66c8f678e4c03f5b1f9a9ca942bd3041d8d72e17f459665b495
3
+ size 1168138808
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16060522496
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
296
+ "model.norm.weight": "model-00004-of-00004.safetensors"
297
+ }
298
+ }
runs/Oct02_11-31-31_ed5c6d72dca0/events.out.tfevents.1727868774.ed5c6d72dca0.4210.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ff504100ac2af427649887f5e24c6f4bb06b21c19fac6b011a8b64b6d88ad49
3
+ size 120221
runs/Oct02_11-31-31_ed5c6d72dca0/events.out.tfevents.1727874536.ed5c6d72dca0.4210.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bd7dc567a27284dee1770119888a594f692c382c8c8e776eaae0b9370317af5
3
+ size 359
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,2065 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "padding_side": "right",
2063
+ "split_special_tokens": false,
2064
+ "tokenizer_class": "PreTrainedTokenizerFast"
2065
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 8.994283294516197,
3
+ "total_flos": 5.095460800932741e+17,
4
+ "train_loss": 0.9683849982173653,
5
+ "train_runtime": 5676.759,
6
+ "train_samples_per_second": 7.488,
7
+ "train_steps_per_second": 0.935
8
+ }
trainer_log.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
trainer_state.json ADDED
@@ -0,0 +1,3839 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 8.994283294516197,
5
+ "eval_steps": 500,
6
+ "global_step": 5310,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01693838661867457,
13
+ "grad_norm": 5.0625,
14
+ "learning_rate": 1.8832391713747647e-07,
15
+ "loss": 2.0482,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.03387677323734914,
20
+ "grad_norm": 5.59375,
21
+ "learning_rate": 3.7664783427495294e-07,
22
+ "loss": 2.069,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.050815159856023716,
27
+ "grad_norm": 5.96875,
28
+ "learning_rate": 5.649717514124295e-07,
29
+ "loss": 2.0861,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.06775354647469828,
34
+ "grad_norm": 5.65625,
35
+ "learning_rate": 7.532956685499059e-07,
36
+ "loss": 2.0413,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.08469193309337286,
41
+ "grad_norm": 16.125,
42
+ "learning_rate": 9.416195856873824e-07,
43
+ "loss": 2.0095,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.10163031971204743,
48
+ "grad_norm": 17.75,
49
+ "learning_rate": 1.129943502824859e-06,
50
+ "loss": 2.0333,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.118568706330722,
55
+ "grad_norm": 14.3125,
56
+ "learning_rate": 1.3182674199623351e-06,
57
+ "loss": 2.0062,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.13550709294939656,
62
+ "grad_norm": 15.5625,
63
+ "learning_rate": 1.5065913370998117e-06,
64
+ "loss": 1.9655,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.15244547956807114,
69
+ "grad_norm": 14.4375,
70
+ "learning_rate": 1.6949152542372882e-06,
71
+ "loss": 1.9698,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.16938386618674572,
76
+ "grad_norm": 3.4375,
77
+ "learning_rate": 1.8832391713747648e-06,
78
+ "loss": 1.9211,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.18632225280542028,
83
+ "grad_norm": 2.703125,
84
+ "learning_rate": 2.071563088512241e-06,
85
+ "loss": 1.9071,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.20326063942409486,
90
+ "grad_norm": 3.453125,
91
+ "learning_rate": 2.259887005649718e-06,
92
+ "loss": 1.8766,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.22019902604276942,
97
+ "grad_norm": 2.9375,
98
+ "learning_rate": 2.448210922787194e-06,
99
+ "loss": 1.8211,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.237137412661444,
104
+ "grad_norm": 3.859375,
105
+ "learning_rate": 2.6365348399246702e-06,
106
+ "loss": 1.7678,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.2540757992801186,
111
+ "grad_norm": 2.515625,
112
+ "learning_rate": 2.8248587570621473e-06,
113
+ "loss": 1.6984,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.2710141858987931,
118
+ "grad_norm": 2.671875,
119
+ "learning_rate": 3.0131826741996235e-06,
120
+ "loss": 1.6916,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.2879525725174677,
125
+ "grad_norm": 2.515625,
126
+ "learning_rate": 3.2015065913371e-06,
127
+ "loss": 1.7083,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.3048909591361423,
132
+ "grad_norm": 2.609375,
133
+ "learning_rate": 3.3898305084745763e-06,
134
+ "loss": 1.7021,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.32182934575481686,
139
+ "grad_norm": 3.109375,
140
+ "learning_rate": 3.5781544256120534e-06,
141
+ "loss": 1.654,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.33876773237349145,
146
+ "grad_norm": 1.875,
147
+ "learning_rate": 3.7664783427495296e-06,
148
+ "loss": 1.6125,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.355706118992166,
153
+ "grad_norm": 1.9765625,
154
+ "learning_rate": 3.954802259887006e-06,
155
+ "loss": 1.6243,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.37264450561084056,
160
+ "grad_norm": 2.046875,
161
+ "learning_rate": 4.143126177024482e-06,
162
+ "loss": 1.6311,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.38958289222951514,
167
+ "grad_norm": 2.375,
168
+ "learning_rate": 4.331450094161959e-06,
169
+ "loss": 1.6088,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.4065212788481897,
174
+ "grad_norm": 1.9765625,
175
+ "learning_rate": 4.519774011299436e-06,
176
+ "loss": 1.6126,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.42345966546686425,
181
+ "grad_norm": 2.0,
182
+ "learning_rate": 4.7080979284369114e-06,
183
+ "loss": 1.5862,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.44039805208553884,
188
+ "grad_norm": 1.9296875,
189
+ "learning_rate": 4.896421845574388e-06,
190
+ "loss": 1.5869,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.4573364387042134,
195
+ "grad_norm": 2.03125,
196
+ "learning_rate": 5.084745762711865e-06,
197
+ "loss": 1.568,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.474274825322888,
202
+ "grad_norm": 2.234375,
203
+ "learning_rate": 5.2730696798493405e-06,
204
+ "loss": 1.4917,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.4912132119415626,
209
+ "grad_norm": 3.0,
210
+ "learning_rate": 5.461393596986818e-06,
211
+ "loss": 1.5614,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.5081515985602372,
216
+ "grad_norm": 2.09375,
217
+ "learning_rate": 5.6497175141242946e-06,
218
+ "loss": 1.5684,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.5250899851789117,
223
+ "grad_norm": 1.765625,
224
+ "learning_rate": 5.83804143126177e-06,
225
+ "loss": 1.5933,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.5420283717975862,
230
+ "grad_norm": 1.953125,
231
+ "learning_rate": 6.026365348399247e-06,
232
+ "loss": 1.5864,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.5589667584162609,
237
+ "grad_norm": 1.9296875,
238
+ "learning_rate": 6.2146892655367244e-06,
239
+ "loss": 1.539,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.5759051450349354,
244
+ "grad_norm": 2.125,
245
+ "learning_rate": 6.4030131826742e-06,
246
+ "loss": 1.4972,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.59284353165361,
251
+ "grad_norm": 1.765625,
252
+ "learning_rate": 6.591337099811677e-06,
253
+ "loss": 1.5136,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.6097819182722846,
258
+ "grad_norm": 1.921875,
259
+ "learning_rate": 6.779661016949153e-06,
260
+ "loss": 1.5159,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.6267203048909591,
265
+ "grad_norm": 1.8125,
266
+ "learning_rate": 6.96798493408663e-06,
267
+ "loss": 1.4829,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.6436586915096337,
272
+ "grad_norm": 1.9296875,
273
+ "learning_rate": 7.156308851224107e-06,
274
+ "loss": 1.4972,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.6605970781283083,
279
+ "grad_norm": 2.140625,
280
+ "learning_rate": 7.3446327683615825e-06,
281
+ "loss": 1.4115,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.6775354647469829,
286
+ "grad_norm": 2.296875,
287
+ "learning_rate": 7.532956685499059e-06,
288
+ "loss": 1.5167,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.6944738513656574,
293
+ "grad_norm": 1.96875,
294
+ "learning_rate": 7.721280602636536e-06,
295
+ "loss": 1.4496,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.711412237984332,
300
+ "grad_norm": 1.7734375,
301
+ "learning_rate": 7.909604519774012e-06,
302
+ "loss": 1.4258,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.7283506246030066,
307
+ "grad_norm": 3.28125,
308
+ "learning_rate": 8.097928436911489e-06,
309
+ "loss": 1.498,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.7452890112216811,
314
+ "grad_norm": 2.078125,
315
+ "learning_rate": 8.286252354048965e-06,
316
+ "loss": 1.4588,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.7622273978403558,
321
+ "grad_norm": 2.03125,
322
+ "learning_rate": 8.47457627118644e-06,
323
+ "loss": 1.4085,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.7791657844590303,
328
+ "grad_norm": 1.9765625,
329
+ "learning_rate": 8.662900188323918e-06,
330
+ "loss": 1.4479,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.7961041710777048,
335
+ "grad_norm": 2.25,
336
+ "learning_rate": 8.851224105461394e-06,
337
+ "loss": 1.4711,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.8130425576963795,
342
+ "grad_norm": 2.078125,
343
+ "learning_rate": 9.039548022598871e-06,
344
+ "loss": 1.4004,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.829980944315054,
349
+ "grad_norm": 2.09375,
350
+ "learning_rate": 9.227871939736347e-06,
351
+ "loss": 1.3785,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.8469193309337285,
356
+ "grad_norm": 1.765625,
357
+ "learning_rate": 9.416195856873823e-06,
358
+ "loss": 1.3784,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.8469193309337285,
363
+ "eval_loss": 1.401244044303894,
364
+ "eval_runtime": 21.2893,
365
+ "eval_samples_per_second": 24.66,
366
+ "eval_steps_per_second": 24.66,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 0.8638577175524031,
371
+ "grad_norm": 1.96875,
372
+ "learning_rate": 9.6045197740113e-06,
373
+ "loss": 1.4401,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 0.8807961041710777,
378
+ "grad_norm": 1.6640625,
379
+ "learning_rate": 9.792843691148776e-06,
380
+ "loss": 1.4191,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 0.8977344907897523,
385
+ "grad_norm": 1.6015625,
386
+ "learning_rate": 9.981167608286254e-06,
387
+ "loss": 1.3972,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 0.9146728774084268,
392
+ "grad_norm": 1.7421875,
393
+ "learning_rate": 9.999912491660088e-06,
394
+ "loss": 1.4051,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 0.9316112640271014,
399
+ "grad_norm": 1.8984375,
400
+ "learning_rate": 9.999609997627497e-06,
401
+ "loss": 1.3855,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 0.948549650645776,
406
+ "grad_norm": 1.765625,
407
+ "learning_rate": 9.999091450621204e-06,
408
+ "loss": 1.4033,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 0.9654880372644505,
413
+ "grad_norm": 1.640625,
414
+ "learning_rate": 9.99835687304968e-06,
415
+ "loss": 1.4429,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 0.9824264238831252,
420
+ "grad_norm": 1.8515625,
421
+ "learning_rate": 9.997406296656937e-06,
422
+ "loss": 1.3925,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 0.9993648105017997,
427
+ "grad_norm": 1.78125,
428
+ "learning_rate": 9.996239762521152e-06,
429
+ "loss": 1.4055,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.0163031971204743,
434
+ "grad_norm": 2.203125,
435
+ "learning_rate": 9.994857321052887e-06,
436
+ "loss": 1.2929,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.0332415837391489,
441
+ "grad_norm": 1.8203125,
442
+ "learning_rate": 9.993259031992921e-06,
443
+ "loss": 1.2752,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.0501799703578234,
448
+ "grad_norm": 1.59375,
449
+ "learning_rate": 9.991444964409665e-06,
450
+ "loss": 1.3491,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.067118356976498,
455
+ "grad_norm": 1.8515625,
456
+ "learning_rate": 9.989415196696169e-06,
457
+ "loss": 1.3204,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.0840567435951725,
462
+ "grad_norm": 1.625,
463
+ "learning_rate": 9.98716981656675e-06,
464
+ "loss": 1.3425,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.1009951302138472,
469
+ "grad_norm": 1.921875,
470
+ "learning_rate": 9.98470892105318e-06,
471
+ "loss": 1.3116,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.1179335168325217,
476
+ "grad_norm": 1.8203125,
477
+ "learning_rate": 9.982032616500516e-06,
478
+ "loss": 1.307,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.1348719034511963,
483
+ "grad_norm": 1.875,
484
+ "learning_rate": 9.979141018562494e-06,
485
+ "loss": 1.3132,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.1518102900698708,
490
+ "grad_norm": 1.84375,
491
+ "learning_rate": 9.976034252196524e-06,
492
+ "loss": 1.3304,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.1687486766885455,
497
+ "grad_norm": 1.6796875,
498
+ "learning_rate": 9.9727124516583e-06,
499
+ "loss": 1.347,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.18568706330722,
504
+ "grad_norm": 1.734375,
505
+ "learning_rate": 9.969175760495997e-06,
506
+ "loss": 1.2844,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.2026254499258946,
511
+ "grad_norm": 1.6953125,
512
+ "learning_rate": 9.965424331544064e-06,
513
+ "loss": 1.2891,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.2195638365445691,
518
+ "grad_norm": 1.828125,
519
+ "learning_rate": 9.961458326916624e-06,
520
+ "loss": 1.3258,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.2365022231632437,
525
+ "grad_norm": 1.609375,
526
+ "learning_rate": 9.95727791800046e-06,
527
+ "loss": 1.2944,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.2534406097819182,
532
+ "grad_norm": 1.6171875,
533
+ "learning_rate": 9.952883285447622e-06,
534
+ "loss": 1.2602,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.2703789964005927,
539
+ "grad_norm": 1.796875,
540
+ "learning_rate": 9.948274619167608e-06,
541
+ "loss": 1.2353,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.2873173830192675,
546
+ "grad_norm": 1.6953125,
547
+ "learning_rate": 9.943452118319165e-06,
548
+ "loss": 1.2749,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.304255769637942,
553
+ "grad_norm": 1.765625,
554
+ "learning_rate": 9.938415991301675e-06,
555
+ "loss": 1.2432,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.3211941562566165,
560
+ "grad_norm": 1.625,
561
+ "learning_rate": 9.933166455746159e-06,
562
+ "loss": 1.2824,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.3381325428752913,
567
+ "grad_norm": 1.5703125,
568
+ "learning_rate": 9.927703738505863e-06,
569
+ "loss": 1.2335,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.3550709294939658,
574
+ "grad_norm": 1.5625,
575
+ "learning_rate": 9.922028075646465e-06,
576
+ "loss": 1.3065,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.3720093161126403,
581
+ "grad_norm": 1.5703125,
582
+ "learning_rate": 9.91613971243586e-06,
583
+ "loss": 1.2443,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.3889477027313148,
588
+ "grad_norm": 1.578125,
589
+ "learning_rate": 9.910038903333574e-06,
590
+ "loss": 1.2303,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.4058860893499894,
595
+ "grad_norm": 1.90625,
596
+ "learning_rate": 9.90372591197976e-06,
597
+ "loss": 1.1844,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.422824475968664,
602
+ "grad_norm": 1.53125,
603
+ "learning_rate": 9.89720101118381e-06,
604
+ "loss": 1.2035,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.4397628625873384,
609
+ "grad_norm": 1.421875,
610
+ "learning_rate": 9.890464482912561e-06,
611
+ "loss": 1.2399,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.4567012492060132,
616
+ "grad_norm": 1.578125,
617
+ "learning_rate": 9.88351661827811e-06,
618
+ "loss": 1.227,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.4736396358246877,
623
+ "grad_norm": 1.484375,
624
+ "learning_rate": 9.876357717525245e-06,
625
+ "loss": 1.2589,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.4905780224433622,
630
+ "grad_norm": 1.84375,
631
+ "learning_rate": 9.86898809001845e-06,
632
+ "loss": 1.1935,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.507516409062037,
637
+ "grad_norm": 1.5,
638
+ "learning_rate": 9.861408054228556e-06,
639
+ "loss": 1.2177,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 1.5244547956807115,
644
+ "grad_norm": 1.3828125,
645
+ "learning_rate": 9.853617937718966e-06,
646
+ "loss": 1.2285,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 1.541393182299386,
651
+ "grad_norm": 1.3515625,
652
+ "learning_rate": 9.845618077131508e-06,
653
+ "loss": 1.226,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 1.5583315689180606,
658
+ "grad_norm": 1.421875,
659
+ "learning_rate": 9.837408818171884e-06,
660
+ "loss": 1.2536,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 1.575269955536735,
665
+ "grad_norm": 1.2578125,
666
+ "learning_rate": 9.82899051559472e-06,
667
+ "loss": 1.2041,
668
+ "step": 930
669
+ },
670
+ {
671
+ "epoch": 1.5922083421554096,
672
+ "grad_norm": 1.515625,
673
+ "learning_rate": 9.820363533188257e-06,
674
+ "loss": 1.2279,
675
+ "step": 940
676
+ },
677
+ {
678
+ "epoch": 1.6091467287740842,
679
+ "grad_norm": 1.2421875,
680
+ "learning_rate": 9.811528243758612e-06,
681
+ "loss": 1.1829,
682
+ "step": 950
683
+ },
684
+ {
685
+ "epoch": 1.6260851153927587,
686
+ "grad_norm": 1.6015625,
687
+ "learning_rate": 9.802485029113682e-06,
688
+ "loss": 1.1698,
689
+ "step": 960
690
+ },
691
+ {
692
+ "epoch": 1.6430235020114334,
693
+ "grad_norm": 1.234375,
694
+ "learning_rate": 9.793234280046627e-06,
695
+ "loss": 1.2212,
696
+ "step": 970
697
+ },
698
+ {
699
+ "epoch": 1.659961888630108,
700
+ "grad_norm": 1.234375,
701
+ "learning_rate": 9.783776396318998e-06,
702
+ "loss": 1.1377,
703
+ "step": 980
704
+ },
705
+ {
706
+ "epoch": 1.6769002752487827,
707
+ "grad_norm": 1.3203125,
708
+ "learning_rate": 9.77411178664346e-06,
709
+ "loss": 1.2086,
710
+ "step": 990
711
+ },
712
+ {
713
+ "epoch": 1.6938386618674572,
714
+ "grad_norm": 1.3125,
715
+ "learning_rate": 9.76424086866612e-06,
716
+ "loss": 1.1764,
717
+ "step": 1000
718
+ },
719
+ {
720
+ "epoch": 1.6938386618674572,
721
+ "eval_loss": 1.2227357625961304,
722
+ "eval_runtime": 20.8763,
723
+ "eval_samples_per_second": 25.148,
724
+ "eval_steps_per_second": 25.148,
725
+ "step": 1000
726
+ },
727
+ {
728
+ "epoch": 1.7107770484861318,
729
+ "grad_norm": 1.2421875,
730
+ "learning_rate": 9.754164068948482e-06,
731
+ "loss": 1.1537,
732
+ "step": 1010
733
+ },
734
+ {
735
+ "epoch": 1.7277154351048063,
736
+ "grad_norm": 1.453125,
737
+ "learning_rate": 9.743881822949025e-06,
738
+ "loss": 1.2405,
739
+ "step": 1020
740
+ },
741
+ {
742
+ "epoch": 1.7446538217234808,
743
+ "grad_norm": 1.1875,
744
+ "learning_rate": 9.733394575004373e-06,
745
+ "loss": 1.2403,
746
+ "step": 1030
747
+ },
748
+ {
749
+ "epoch": 1.7615922083421554,
750
+ "grad_norm": 1.40625,
751
+ "learning_rate": 9.722702778310096e-06,
752
+ "loss": 1.152,
753
+ "step": 1040
754
+ },
755
+ {
756
+ "epoch": 1.7785305949608299,
757
+ "grad_norm": 1.265625,
758
+ "learning_rate": 9.711806894901124e-06,
759
+ "loss": 1.1596,
760
+ "step": 1050
761
+ },
762
+ {
763
+ "epoch": 1.7954689815795044,
764
+ "grad_norm": 1.25,
765
+ "learning_rate": 9.700707395631787e-06,
766
+ "loss": 1.1555,
767
+ "step": 1060
768
+ },
769
+ {
770
+ "epoch": 1.8124073681981792,
771
+ "grad_norm": 1.171875,
772
+ "learning_rate": 9.689404760155465e-06,
773
+ "loss": 1.1611,
774
+ "step": 1070
775
+ },
776
+ {
777
+ "epoch": 1.8293457548168537,
778
+ "grad_norm": 1.640625,
779
+ "learning_rate": 9.677899476903857e-06,
780
+ "loss": 1.1727,
781
+ "step": 1080
782
+ },
783
+ {
784
+ "epoch": 1.8462841414355282,
785
+ "grad_norm": 1.2265625,
786
+ "learning_rate": 9.666192043065875e-06,
787
+ "loss": 1.1526,
788
+ "step": 1090
789
+ },
790
+ {
791
+ "epoch": 1.863222528054203,
792
+ "grad_norm": 1.265625,
793
+ "learning_rate": 9.654282964566159e-06,
794
+ "loss": 1.1677,
795
+ "step": 1100
796
+ },
797
+ {
798
+ "epoch": 1.8801609146728775,
799
+ "grad_norm": 1.1953125,
800
+ "learning_rate": 9.642172756043217e-06,
801
+ "loss": 1.1363,
802
+ "step": 1110
803
+ },
804
+ {
805
+ "epoch": 1.897099301291552,
806
+ "grad_norm": 1.1953125,
807
+ "learning_rate": 9.629861940827181e-06,
808
+ "loss": 1.1216,
809
+ "step": 1120
810
+ },
811
+ {
812
+ "epoch": 1.9140376879102265,
813
+ "grad_norm": 1.2109375,
814
+ "learning_rate": 9.617351050917197e-06,
815
+ "loss": 1.1432,
816
+ "step": 1130
817
+ },
818
+ {
819
+ "epoch": 1.930976074528901,
820
+ "grad_norm": 1.0859375,
821
+ "learning_rate": 9.604640626958428e-06,
822
+ "loss": 1.1714,
823
+ "step": 1140
824
+ },
825
+ {
826
+ "epoch": 1.9479144611475756,
827
+ "grad_norm": 1.21875,
828
+ "learning_rate": 9.591731218218694e-06,
829
+ "loss": 1.1999,
830
+ "step": 1150
831
+ },
832
+ {
833
+ "epoch": 1.9648528477662501,
834
+ "grad_norm": 1.078125,
835
+ "learning_rate": 9.57862338256474e-06,
836
+ "loss": 1.1692,
837
+ "step": 1160
838
+ },
839
+ {
840
+ "epoch": 1.9817912343849249,
841
+ "grad_norm": 1.125,
842
+ "learning_rate": 9.565317686438122e-06,
843
+ "loss": 1.1193,
844
+ "step": 1170
845
+ },
846
+ {
847
+ "epoch": 1.9987296210035994,
848
+ "grad_norm": 0.92578125,
849
+ "learning_rate": 9.551814704830734e-06,
850
+ "loss": 1.1596,
851
+ "step": 1180
852
+ },
853
+ {
854
+ "epoch": 2.015668007622274,
855
+ "grad_norm": 0.96875,
856
+ "learning_rate": 9.538115021259956e-06,
857
+ "loss": 1.0715,
858
+ "step": 1190
859
+ },
860
+ {
861
+ "epoch": 2.0326063942409487,
862
+ "grad_norm": 0.9375,
863
+ "learning_rate": 9.52421922774344e-06,
864
+ "loss": 1.0312,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.049544780859623,
869
+ "grad_norm": 0.9609375,
870
+ "learning_rate": 9.510127924773529e-06,
871
+ "loss": 1.0574,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.0664831674782977,
876
+ "grad_norm": 0.95703125,
877
+ "learning_rate": 9.4958417212913e-06,
878
+ "loss": 1.0862,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.0834215540969723,
883
+ "grad_norm": 0.96875,
884
+ "learning_rate": 9.481361234660258e-06,
885
+ "loss": 1.0776,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.100359940715647,
890
+ "grad_norm": 0.95703125,
891
+ "learning_rate": 9.466687090639652e-06,
892
+ "loss": 1.088,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.1172983273343213,
897
+ "grad_norm": 0.9296875,
898
+ "learning_rate": 9.451819923357435e-06,
899
+ "loss": 1.1108,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.134236713952996,
904
+ "grad_norm": 0.9921875,
905
+ "learning_rate": 9.436760375282858e-06,
906
+ "loss": 1.0786,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 2.1511751005716704,
911
+ "grad_norm": 0.87890625,
912
+ "learning_rate": 9.421509097198715e-06,
913
+ "loss": 1.0269,
914
+ "step": 1270
915
+ },
916
+ {
917
+ "epoch": 2.168113487190345,
918
+ "grad_norm": 1.171875,
919
+ "learning_rate": 9.406066748173208e-06,
920
+ "loss": 1.1046,
921
+ "step": 1280
922
+ },
923
+ {
924
+ "epoch": 2.18505187380902,
925
+ "grad_norm": 0.9140625,
926
+ "learning_rate": 9.390433995531473e-06,
927
+ "loss": 1.0651,
928
+ "step": 1290
929
+ },
930
+ {
931
+ "epoch": 2.2019902604276944,
932
+ "grad_norm": 0.91796875,
933
+ "learning_rate": 9.374611514826746e-06,
934
+ "loss": 1.0212,
935
+ "step": 1300
936
+ },
937
+ {
938
+ "epoch": 2.218928647046369,
939
+ "grad_norm": 1.03125,
940
+ "learning_rate": 9.358599989811158e-06,
941
+ "loss": 1.0786,
942
+ "step": 1310
943
+ },
944
+ {
945
+ "epoch": 2.2358670336650435,
946
+ "grad_norm": 1.046875,
947
+ "learning_rate": 9.3424001124062e-06,
948
+ "loss": 1.0125,
949
+ "step": 1320
950
+ },
951
+ {
952
+ "epoch": 2.252805420283718,
953
+ "grad_norm": 0.90234375,
954
+ "learning_rate": 9.326012582672814e-06,
955
+ "loss": 1.0756,
956
+ "step": 1330
957
+ },
958
+ {
959
+ "epoch": 2.2697438069023925,
960
+ "grad_norm": 1.015625,
961
+ "learning_rate": 9.309438108781143e-06,
962
+ "loss": 1.1165,
963
+ "step": 1340
964
+ },
965
+ {
966
+ "epoch": 2.286682193521067,
967
+ "grad_norm": 0.9609375,
968
+ "learning_rate": 9.29267740697993e-06,
969
+ "loss": 1.037,
970
+ "step": 1350
971
+ },
972
+ {
973
+ "epoch": 2.3036205801397416,
974
+ "grad_norm": 1.25,
975
+ "learning_rate": 9.275731201565564e-06,
976
+ "loss": 1.03,
977
+ "step": 1360
978
+ },
979
+ {
980
+ "epoch": 2.320558966758416,
981
+ "grad_norm": 0.93359375,
982
+ "learning_rate": 9.258600224850777e-06,
983
+ "loss": 1.0461,
984
+ "step": 1370
985
+ },
986
+ {
987
+ "epoch": 2.337497353377091,
988
+ "grad_norm": 1.2421875,
989
+ "learning_rate": 9.24128521713301e-06,
990
+ "loss": 1.0065,
991
+ "step": 1380
992
+ },
993
+ {
994
+ "epoch": 2.3544357399957656,
995
+ "grad_norm": 1.0234375,
996
+ "learning_rate": 9.223786926662404e-06,
997
+ "loss": 1.0661,
998
+ "step": 1390
999
+ },
1000
+ {
1001
+ "epoch": 2.37137412661444,
1002
+ "grad_norm": 1.0078125,
1003
+ "learning_rate": 9.20610610960948e-06,
1004
+ "loss": 1.0764,
1005
+ "step": 1400
1006
+ },
1007
+ {
1008
+ "epoch": 2.3883125132331147,
1009
+ "grad_norm": 1.015625,
1010
+ "learning_rate": 9.188243530032458e-06,
1011
+ "loss": 1.0448,
1012
+ "step": 1410
1013
+ },
1014
+ {
1015
+ "epoch": 2.405250899851789,
1016
+ "grad_norm": 0.984375,
1017
+ "learning_rate": 9.170199959844232e-06,
1018
+ "loss": 1.0695,
1019
+ "step": 1420
1020
+ },
1021
+ {
1022
+ "epoch": 2.4221892864704637,
1023
+ "grad_norm": 1.015625,
1024
+ "learning_rate": 9.15197617877902e-06,
1025
+ "loss": 0.9995,
1026
+ "step": 1430
1027
+ },
1028
+ {
1029
+ "epoch": 2.4391276730891382,
1030
+ "grad_norm": 1.015625,
1031
+ "learning_rate": 9.133572974358669e-06,
1032
+ "loss": 1.0307,
1033
+ "step": 1440
1034
+ },
1035
+ {
1036
+ "epoch": 2.4560660597078128,
1037
+ "grad_norm": 1.1328125,
1038
+ "learning_rate": 9.114991141858619e-06,
1039
+ "loss": 1.0004,
1040
+ "step": 1450
1041
+ },
1042
+ {
1043
+ "epoch": 2.4730044463264873,
1044
+ "grad_norm": 1.390625,
1045
+ "learning_rate": 9.096231484273535e-06,
1046
+ "loss": 1.0553,
1047
+ "step": 1460
1048
+ },
1049
+ {
1050
+ "epoch": 2.489942832945162,
1051
+ "grad_norm": 1.1328125,
1052
+ "learning_rate": 9.077294812282615e-06,
1053
+ "loss": 1.0481,
1054
+ "step": 1470
1055
+ },
1056
+ {
1057
+ "epoch": 2.5068812195638364,
1058
+ "grad_norm": 1.203125,
1059
+ "learning_rate": 9.058181944214547e-06,
1060
+ "loss": 1.0438,
1061
+ "step": 1480
1062
+ },
1063
+ {
1064
+ "epoch": 2.523819606182511,
1065
+ "grad_norm": 1.0234375,
1066
+ "learning_rate": 9.038893706012153e-06,
1067
+ "loss": 1.0458,
1068
+ "step": 1490
1069
+ },
1070
+ {
1071
+ "epoch": 2.5407579928011854,
1072
+ "grad_norm": 1.4765625,
1073
+ "learning_rate": 9.01943093119669e-06,
1074
+ "loss": 0.9808,
1075
+ "step": 1500
1076
+ },
1077
+ {
1078
+ "epoch": 2.5407579928011854,
1079
+ "eval_loss": 1.1499994993209839,
1080
+ "eval_runtime": 21.1383,
1081
+ "eval_samples_per_second": 24.836,
1082
+ "eval_steps_per_second": 24.836,
1083
+ "step": 1500
1084
+ },
1085
+ {
1086
+ "epoch": 2.5576963794198604,
1087
+ "grad_norm": 1.4609375,
1088
+ "learning_rate": 8.999794460831836e-06,
1089
+ "loss": 1.0539,
1090
+ "step": 1510
1091
+ },
1092
+ {
1093
+ "epoch": 2.574634766038535,
1094
+ "grad_norm": 1.6640625,
1095
+ "learning_rate": 8.979985143487343e-06,
1096
+ "loss": 1.046,
1097
+ "step": 1520
1098
+ },
1099
+ {
1100
+ "epoch": 2.5915731526572094,
1101
+ "grad_norm": 1.4140625,
1102
+ "learning_rate": 8.960003835202369e-06,
1103
+ "loss": 1.0188,
1104
+ "step": 1530
1105
+ },
1106
+ {
1107
+ "epoch": 2.608511539275884,
1108
+ "grad_norm": 1.453125,
1109
+ "learning_rate": 8.939851399448478e-06,
1110
+ "loss": 1.0423,
1111
+ "step": 1540
1112
+ },
1113
+ {
1114
+ "epoch": 2.6254499258945585,
1115
+ "grad_norm": 2.921875,
1116
+ "learning_rate": 8.919528707092333e-06,
1117
+ "loss": 1.085,
1118
+ "step": 1550
1119
+ },
1120
+ {
1121
+ "epoch": 2.642388312513233,
1122
+ "grad_norm": 2.859375,
1123
+ "learning_rate": 8.899036636358058e-06,
1124
+ "loss": 1.0252,
1125
+ "step": 1560
1126
+ },
1127
+ {
1128
+ "epoch": 2.6593266991319076,
1129
+ "grad_norm": 3.125,
1130
+ "learning_rate": 8.878376072789292e-06,
1131
+ "loss": 1.0246,
1132
+ "step": 1570
1133
+ },
1134
+ {
1135
+ "epoch": 2.6762650857505825,
1136
+ "grad_norm": 2.78125,
1137
+ "learning_rate": 8.857547909210913e-06,
1138
+ "loss": 1.0358,
1139
+ "step": 1580
1140
+ },
1141
+ {
1142
+ "epoch": 2.693203472369257,
1143
+ "grad_norm": 2.59375,
1144
+ "learning_rate": 8.836553045690462e-06,
1145
+ "loss": 1.0746,
1146
+ "step": 1590
1147
+ },
1148
+ {
1149
+ "epoch": 2.7101418589879316,
1150
+ "grad_norm": 3.96875,
1151
+ "learning_rate": 8.81539238949925e-06,
1152
+ "loss": 1.0806,
1153
+ "step": 1600
1154
+ },
1155
+ {
1156
+ "epoch": 2.727080245606606,
1157
+ "grad_norm": 4.15625,
1158
+ "learning_rate": 8.794066855073136e-06,
1159
+ "loss": 0.9917,
1160
+ "step": 1610
1161
+ },
1162
+ {
1163
+ "epoch": 2.7440186322252806,
1164
+ "grad_norm": 4.5625,
1165
+ "learning_rate": 8.772577363973032e-06,
1166
+ "loss": 1.0071,
1167
+ "step": 1620
1168
+ },
1169
+ {
1170
+ "epoch": 2.760957018843955,
1171
+ "grad_norm": 3.25,
1172
+ "learning_rate": 8.750924844845065e-06,
1173
+ "loss": 1.0139,
1174
+ "step": 1630
1175
+ },
1176
+ {
1177
+ "epoch": 2.7778954054626297,
1178
+ "grad_norm": 4.25,
1179
+ "learning_rate": 8.729110233380445e-06,
1180
+ "loss": 1.0684,
1181
+ "step": 1640
1182
+ },
1183
+ {
1184
+ "epoch": 2.7948337920813042,
1185
+ "grad_norm": 9.125,
1186
+ "learning_rate": 8.707134472275042e-06,
1187
+ "loss": 0.9606,
1188
+ "step": 1650
1189
+ },
1190
+ {
1191
+ "epoch": 2.8117721786999788,
1192
+ "grad_norm": 7.78125,
1193
+ "learning_rate": 8.684998511188634e-06,
1194
+ "loss": 1.0529,
1195
+ "step": 1660
1196
+ },
1197
+ {
1198
+ "epoch": 2.8287105653186533,
1199
+ "grad_norm": 7.34375,
1200
+ "learning_rate": 8.662703306703878e-06,
1201
+ "loss": 1.0939,
1202
+ "step": 1670
1203
+ },
1204
+ {
1205
+ "epoch": 2.845648951937328,
1206
+ "grad_norm": 8.375,
1207
+ "learning_rate": 8.640249822284975e-06,
1208
+ "loss": 1.0322,
1209
+ "step": 1680
1210
+ },
1211
+ {
1212
+ "epoch": 2.8625873385560023,
1213
+ "grad_norm": 7.40625,
1214
+ "learning_rate": 8.617639028236021e-06,
1215
+ "loss": 1.0303,
1216
+ "step": 1690
1217
+ },
1218
+ {
1219
+ "epoch": 2.879525725174677,
1220
+ "grad_norm": 2.625,
1221
+ "learning_rate": 8.59487190165909e-06,
1222
+ "loss": 1.0173,
1223
+ "step": 1700
1224
+ },
1225
+ {
1226
+ "epoch": 2.896464111793352,
1227
+ "grad_norm": 2.328125,
1228
+ "learning_rate": 8.571949426412002e-06,
1229
+ "loss": 1.0218,
1230
+ "step": 1710
1231
+ },
1232
+ {
1233
+ "epoch": 2.9134024984120264,
1234
+ "grad_norm": 2.140625,
1235
+ "learning_rate": 8.54887259306581e-06,
1236
+ "loss": 1.0029,
1237
+ "step": 1720
1238
+ },
1239
+ {
1240
+ "epoch": 2.930340885030701,
1241
+ "grad_norm": 2.28125,
1242
+ "learning_rate": 8.525642398861997e-06,
1243
+ "loss": 1.0295,
1244
+ "step": 1730
1245
+ },
1246
+ {
1247
+ "epoch": 2.9472792716493754,
1248
+ "grad_norm": 2.5,
1249
+ "learning_rate": 8.50225984766937e-06,
1250
+ "loss": 1.0432,
1251
+ "step": 1740
1252
+ },
1253
+ {
1254
+ "epoch": 2.96421765826805,
1255
+ "grad_norm": 2.0625,
1256
+ "learning_rate": 8.478725949940687e-06,
1257
+ "loss": 1.026,
1258
+ "step": 1750
1259
+ },
1260
+ {
1261
+ "epoch": 2.9811560448867245,
1262
+ "grad_norm": 2.265625,
1263
+ "learning_rate": 8.455041722668993e-06,
1264
+ "loss": 1.0523,
1265
+ "step": 1760
1266
+ },
1267
+ {
1268
+ "epoch": 2.998094431505399,
1269
+ "grad_norm": 1.8671875,
1270
+ "learning_rate": 8.43120818934367e-06,
1271
+ "loss": 1.0287,
1272
+ "step": 1770
1273
+ },
1274
+ {
1275
+ "epoch": 3.0150328181240735,
1276
+ "grad_norm": 2.109375,
1277
+ "learning_rate": 8.407226379906197e-06,
1278
+ "loss": 0.9998,
1279
+ "step": 1780
1280
+ },
1281
+ {
1282
+ "epoch": 3.031971204742748,
1283
+ "grad_norm": 2.140625,
1284
+ "learning_rate": 8.383097330705664e-06,
1285
+ "loss": 1.0157,
1286
+ "step": 1790
1287
+ },
1288
+ {
1289
+ "epoch": 3.048909591361423,
1290
+ "grad_norm": 1.8828125,
1291
+ "learning_rate": 8.358822084453964e-06,
1292
+ "loss": 0.9514,
1293
+ "step": 1800
1294
+ },
1295
+ {
1296
+ "epoch": 3.0658479779800976,
1297
+ "grad_norm": 1.796875,
1298
+ "learning_rate": 8.334401690180755e-06,
1299
+ "loss": 1.0163,
1300
+ "step": 1810
1301
+ },
1302
+ {
1303
+ "epoch": 3.082786364598772,
1304
+ "grad_norm": 1.8828125,
1305
+ "learning_rate": 8.30983720318811e-06,
1306
+ "loss": 0.969,
1307
+ "step": 1820
1308
+ },
1309
+ {
1310
+ "epoch": 3.0997247512174466,
1311
+ "grad_norm": 1.8203125,
1312
+ "learning_rate": 8.285129685004922e-06,
1313
+ "loss": 0.9769,
1314
+ "step": 1830
1315
+ },
1316
+ {
1317
+ "epoch": 3.116663137836121,
1318
+ "grad_norm": 2.09375,
1319
+ "learning_rate": 8.260280203341026e-06,
1320
+ "loss": 0.9997,
1321
+ "step": 1840
1322
+ },
1323
+ {
1324
+ "epoch": 3.1336015244547957,
1325
+ "grad_norm": 1.828125,
1326
+ "learning_rate": 8.235289832041066e-06,
1327
+ "loss": 0.9577,
1328
+ "step": 1850
1329
+ },
1330
+ {
1331
+ "epoch": 3.15053991107347,
1332
+ "grad_norm": 2.4375,
1333
+ "learning_rate": 8.210159651038081e-06,
1334
+ "loss": 0.9457,
1335
+ "step": 1860
1336
+ },
1337
+ {
1338
+ "epoch": 3.1674782976921447,
1339
+ "grad_norm": 1.7734375,
1340
+ "learning_rate": 8.184890746306848e-06,
1341
+ "loss": 0.9381,
1342
+ "step": 1870
1343
+ },
1344
+ {
1345
+ "epoch": 3.1844166843108193,
1346
+ "grad_norm": 1.96875,
1347
+ "learning_rate": 8.15948420981694e-06,
1348
+ "loss": 0.9709,
1349
+ "step": 1880
1350
+ },
1351
+ {
1352
+ "epoch": 3.201355070929494,
1353
+ "grad_norm": 1.8125,
1354
+ "learning_rate": 8.133941139485551e-06,
1355
+ "loss": 0.9769,
1356
+ "step": 1890
1357
+ },
1358
+ {
1359
+ "epoch": 3.2182934575481683,
1360
+ "grad_norm": 1.875,
1361
+ "learning_rate": 8.108262639130038e-06,
1362
+ "loss": 0.9064,
1363
+ "step": 1900
1364
+ },
1365
+ {
1366
+ "epoch": 3.2352318441668433,
1367
+ "grad_norm": 1.71875,
1368
+ "learning_rate": 8.082449818420227e-06,
1369
+ "loss": 0.9944,
1370
+ "step": 1910
1371
+ },
1372
+ {
1373
+ "epoch": 3.252170230785518,
1374
+ "grad_norm": 2.125,
1375
+ "learning_rate": 8.056503792830458e-06,
1376
+ "loss": 0.9484,
1377
+ "step": 1920
1378
+ },
1379
+ {
1380
+ "epoch": 3.2691086174041923,
1381
+ "grad_norm": 1.8046875,
1382
+ "learning_rate": 8.030425683591391e-06,
1383
+ "loss": 0.9666,
1384
+ "step": 1930
1385
+ },
1386
+ {
1387
+ "epoch": 3.286047004022867,
1388
+ "grad_norm": 1.890625,
1389
+ "learning_rate": 8.004216617641532e-06,
1390
+ "loss": 0.9871,
1391
+ "step": 1940
1392
+ },
1393
+ {
1394
+ "epoch": 3.3029853906415414,
1395
+ "grad_norm": 1.765625,
1396
+ "learning_rate": 7.977877727578556e-06,
1397
+ "loss": 0.9462,
1398
+ "step": 1950
1399
+ },
1400
+ {
1401
+ "epoch": 3.319923777260216,
1402
+ "grad_norm": 2.09375,
1403
+ "learning_rate": 7.951410151610343e-06,
1404
+ "loss": 0.9509,
1405
+ "step": 1960
1406
+ },
1407
+ {
1408
+ "epoch": 3.3368621638788905,
1409
+ "grad_norm": 1.7734375,
1410
+ "learning_rate": 7.92481503350581e-06,
1411
+ "loss": 0.9299,
1412
+ "step": 1970
1413
+ },
1414
+ {
1415
+ "epoch": 3.353800550497565,
1416
+ "grad_norm": 1.734375,
1417
+ "learning_rate": 7.898093522545471e-06,
1418
+ "loss": 0.9824,
1419
+ "step": 1980
1420
+ },
1421
+ {
1422
+ "epoch": 3.3707389371162395,
1423
+ "grad_norm": 1.78125,
1424
+ "learning_rate": 7.871246773471779e-06,
1425
+ "loss": 0.9336,
1426
+ "step": 1990
1427
+ },
1428
+ {
1429
+ "epoch": 3.3876773237349145,
1430
+ "grad_norm": 2.015625,
1431
+ "learning_rate": 7.844275946439216e-06,
1432
+ "loss": 0.9778,
1433
+ "step": 2000
1434
+ },
1435
+ {
1436
+ "epoch": 3.3876773237349145,
1437
+ "eval_loss": 1.1204777956008911,
1438
+ "eval_runtime": 20.947,
1439
+ "eval_samples_per_second": 25.063,
1440
+ "eval_steps_per_second": 25.063,
1441
+ "step": 2000
1442
+ },
1443
+ {
1444
+ "epoch": 3.404615710353589,
1445
+ "grad_norm": 2.359375,
1446
+ "learning_rate": 7.817182206964177e-06,
1447
+ "loss": 0.9817,
1448
+ "step": 2010
1449
+ },
1450
+ {
1451
+ "epoch": 3.4215540969722635,
1452
+ "grad_norm": 2.0625,
1453
+ "learning_rate": 7.789966725874578e-06,
1454
+ "loss": 0.9942,
1455
+ "step": 2020
1456
+ },
1457
+ {
1458
+ "epoch": 3.438492483590938,
1459
+ "grad_norm": 1.734375,
1460
+ "learning_rate": 7.76263067925928e-06,
1461
+ "loss": 0.9783,
1462
+ "step": 2030
1463
+ },
1464
+ {
1465
+ "epoch": 3.4554308702096126,
1466
+ "grad_norm": 1.796875,
1467
+ "learning_rate": 7.735175248417255e-06,
1468
+ "loss": 0.9551,
1469
+ "step": 2040
1470
+ },
1471
+ {
1472
+ "epoch": 3.472369256828287,
1473
+ "grad_norm": 2.046875,
1474
+ "learning_rate": 7.707601619806547e-06,
1475
+ "loss": 0.9592,
1476
+ "step": 2050
1477
+ },
1478
+ {
1479
+ "epoch": 3.4893076434469616,
1480
+ "grad_norm": 2.40625,
1481
+ "learning_rate": 7.679910984992988e-06,
1482
+ "loss": 0.902,
1483
+ "step": 2060
1484
+ },
1485
+ {
1486
+ "epoch": 3.506246030065636,
1487
+ "grad_norm": 2.203125,
1488
+ "learning_rate": 7.652104540598712e-06,
1489
+ "loss": 0.9763,
1490
+ "step": 2070
1491
+ },
1492
+ {
1493
+ "epoch": 3.5231844166843107,
1494
+ "grad_norm": 2.0625,
1495
+ "learning_rate": 7.6241834882504516e-06,
1496
+ "loss": 0.9522,
1497
+ "step": 2080
1498
+ },
1499
+ {
1500
+ "epoch": 3.5401228033029852,
1501
+ "grad_norm": 2.140625,
1502
+ "learning_rate": 7.596149034527594e-06,
1503
+ "loss": 0.992,
1504
+ "step": 2090
1505
+ },
1506
+ {
1507
+ "epoch": 3.5570611899216598,
1508
+ "grad_norm": 1.859375,
1509
+ "learning_rate": 7.5680023909100545e-06,
1510
+ "loss": 0.9366,
1511
+ "step": 2100
1512
+ },
1513
+ {
1514
+ "epoch": 3.5739995765403343,
1515
+ "grad_norm": 1.7421875,
1516
+ "learning_rate": 7.539744773725916e-06,
1517
+ "loss": 0.9888,
1518
+ "step": 2110
1519
+ },
1520
+ {
1521
+ "epoch": 3.5909379631590093,
1522
+ "grad_norm": 1.71875,
1523
+ "learning_rate": 7.511377404098876e-06,
1524
+ "loss": 0.9801,
1525
+ "step": 2120
1526
+ },
1527
+ {
1528
+ "epoch": 3.607876349777684,
1529
+ "grad_norm": 2.0,
1530
+ "learning_rate": 7.482901507895463e-06,
1531
+ "loss": 0.9589,
1532
+ "step": 2130
1533
+ },
1534
+ {
1535
+ "epoch": 3.6248147363963583,
1536
+ "grad_norm": 3.65625,
1537
+ "learning_rate": 7.454318315672074e-06,
1538
+ "loss": 0.9926,
1539
+ "step": 2140
1540
+ },
1541
+ {
1542
+ "epoch": 3.641753123015033,
1543
+ "grad_norm": 1.859375,
1544
+ "learning_rate": 7.425629062621784e-06,
1545
+ "loss": 0.9448,
1546
+ "step": 2150
1547
+ },
1548
+ {
1549
+ "epoch": 3.6586915096337074,
1550
+ "grad_norm": 2.140625,
1551
+ "learning_rate": 7.396834988520989e-06,
1552
+ "loss": 0.9507,
1553
+ "step": 2160
1554
+ },
1555
+ {
1556
+ "epoch": 3.675629896252382,
1557
+ "grad_norm": 2.125,
1558
+ "learning_rate": 7.36793733767581e-06,
1559
+ "loss": 0.9719,
1560
+ "step": 2170
1561
+ },
1562
+ {
1563
+ "epoch": 3.6925682828710564,
1564
+ "grad_norm": 2.34375,
1565
+ "learning_rate": 7.338937358868334e-06,
1566
+ "loss": 0.976,
1567
+ "step": 2180
1568
+ },
1569
+ {
1570
+ "epoch": 3.709506669489731,
1571
+ "grad_norm": 2.28125,
1572
+ "learning_rate": 7.309836305302638e-06,
1573
+ "loss": 0.9431,
1574
+ "step": 2190
1575
+ },
1576
+ {
1577
+ "epoch": 3.726445056108406,
1578
+ "grad_norm": 1.734375,
1579
+ "learning_rate": 7.2806354345506525e-06,
1580
+ "loss": 0.9833,
1581
+ "step": 2200
1582
+ },
1583
+ {
1584
+ "epoch": 3.7433834427270805,
1585
+ "grad_norm": 1.859375,
1586
+ "learning_rate": 7.251336008497793e-06,
1587
+ "loss": 0.9356,
1588
+ "step": 2210
1589
+ },
1590
+ {
1591
+ "epoch": 3.760321829345755,
1592
+ "grad_norm": 1.8203125,
1593
+ "learning_rate": 7.221939293288445e-06,
1594
+ "loss": 0.9911,
1595
+ "step": 2220
1596
+ },
1597
+ {
1598
+ "epoch": 3.7772602159644295,
1599
+ "grad_norm": 1.8671875,
1600
+ "learning_rate": 7.192446559271247e-06,
1601
+ "loss": 0.9569,
1602
+ "step": 2230
1603
+ },
1604
+ {
1605
+ "epoch": 3.794198602583104,
1606
+ "grad_norm": 1.875,
1607
+ "learning_rate": 7.162859080944182e-06,
1608
+ "loss": 0.9907,
1609
+ "step": 2240
1610
+ },
1611
+ {
1612
+ "epoch": 3.8111369892017786,
1613
+ "grad_norm": 1.6484375,
1614
+ "learning_rate": 7.133178136899522e-06,
1615
+ "loss": 0.9672,
1616
+ "step": 2250
1617
+ },
1618
+ {
1619
+ "epoch": 3.828075375820453,
1620
+ "grad_norm": 2.359375,
1621
+ "learning_rate": 7.103405009768554e-06,
1622
+ "loss": 0.9754,
1623
+ "step": 2260
1624
+ },
1625
+ {
1626
+ "epoch": 3.8450137624391276,
1627
+ "grad_norm": 1.7421875,
1628
+ "learning_rate": 7.073540986166166e-06,
1629
+ "loss": 0.9548,
1630
+ "step": 2270
1631
+ },
1632
+ {
1633
+ "epoch": 3.861952149057802,
1634
+ "grad_norm": 1.7421875,
1635
+ "learning_rate": 7.0435873566352434e-06,
1636
+ "loss": 0.9682,
1637
+ "step": 2280
1638
+ },
1639
+ {
1640
+ "epoch": 3.8788905356764767,
1641
+ "grad_norm": 1.8515625,
1642
+ "learning_rate": 7.013545415590897e-06,
1643
+ "loss": 0.8956,
1644
+ "step": 2290
1645
+ },
1646
+ {
1647
+ "epoch": 3.895828922295151,
1648
+ "grad_norm": 1.96875,
1649
+ "learning_rate": 6.983416461264527e-06,
1650
+ "loss": 0.9314,
1651
+ "step": 2300
1652
+ },
1653
+ {
1654
+ "epoch": 3.9127673089138257,
1655
+ "grad_norm": 1.890625,
1656
+ "learning_rate": 6.953201795647728e-06,
1657
+ "loss": 0.9101,
1658
+ "step": 2310
1659
+ },
1660
+ {
1661
+ "epoch": 3.9297056955325003,
1662
+ "grad_norm": 1.921875,
1663
+ "learning_rate": 6.922902724436016e-06,
1664
+ "loss": 0.9463,
1665
+ "step": 2320
1666
+ },
1667
+ {
1668
+ "epoch": 3.9466440821511752,
1669
+ "grad_norm": 1.8984375,
1670
+ "learning_rate": 6.892520556972404e-06,
1671
+ "loss": 0.9443,
1672
+ "step": 2330
1673
+ },
1674
+ {
1675
+ "epoch": 3.9635824687698498,
1676
+ "grad_norm": 1.8125,
1677
+ "learning_rate": 6.86205660619083e-06,
1678
+ "loss": 0.9371,
1679
+ "step": 2340
1680
+ },
1681
+ {
1682
+ "epoch": 3.9805208553885243,
1683
+ "grad_norm": 1.9375,
1684
+ "learning_rate": 6.8315121885594105e-06,
1685
+ "loss": 0.95,
1686
+ "step": 2350
1687
+ },
1688
+ {
1689
+ "epoch": 3.997459242007199,
1690
+ "grad_norm": 1.9140625,
1691
+ "learning_rate": 6.800888624023552e-06,
1692
+ "loss": 0.9412,
1693
+ "step": 2360
1694
+ },
1695
+ {
1696
+ "epoch": 4.014397628625874,
1697
+ "grad_norm": 1.59375,
1698
+ "learning_rate": 6.770187235948916e-06,
1699
+ "loss": 0.8627,
1700
+ "step": 2370
1701
+ },
1702
+ {
1703
+ "epoch": 4.031336015244548,
1704
+ "grad_norm": 1.671875,
1705
+ "learning_rate": 6.739409351064225e-06,
1706
+ "loss": 0.8663,
1707
+ "step": 2380
1708
+ },
1709
+ {
1710
+ "epoch": 4.048274401863223,
1711
+ "grad_norm": 1.8046875,
1712
+ "learning_rate": 6.708556299403935e-06,
1713
+ "loss": 0.8087,
1714
+ "step": 2390
1715
+ },
1716
+ {
1717
+ "epoch": 4.065212788481897,
1718
+ "grad_norm": 1.7578125,
1719
+ "learning_rate": 6.6776294142507535e-06,
1720
+ "loss": 0.8501,
1721
+ "step": 2400
1722
+ },
1723
+ {
1724
+ "epoch": 4.082151175100572,
1725
+ "grad_norm": 1.6328125,
1726
+ "learning_rate": 6.646630032078024e-06,
1727
+ "loss": 0.854,
1728
+ "step": 2410
1729
+ },
1730
+ {
1731
+ "epoch": 4.099089561719246,
1732
+ "grad_norm": 1.5,
1733
+ "learning_rate": 6.615559492491981e-06,
1734
+ "loss": 0.884,
1735
+ "step": 2420
1736
+ },
1737
+ {
1738
+ "epoch": 4.116027948337921,
1739
+ "grad_norm": 1.890625,
1740
+ "learning_rate": 6.584419138173846e-06,
1741
+ "loss": 0.8693,
1742
+ "step": 2430
1743
+ },
1744
+ {
1745
+ "epoch": 4.1329663349565955,
1746
+ "grad_norm": 1.625,
1747
+ "learning_rate": 6.553210314821814e-06,
1748
+ "loss": 0.8397,
1749
+ "step": 2440
1750
+ },
1751
+ {
1752
+ "epoch": 4.14990472157527,
1753
+ "grad_norm": 1.7265625,
1754
+ "learning_rate": 6.521934371092901e-06,
1755
+ "loss": 0.8355,
1756
+ "step": 2450
1757
+ },
1758
+ {
1759
+ "epoch": 4.1668431081939445,
1760
+ "grad_norm": 1.5,
1761
+ "learning_rate": 6.490592658544661e-06,
1762
+ "loss": 0.8784,
1763
+ "step": 2460
1764
+ },
1765
+ {
1766
+ "epoch": 4.183781494812619,
1767
+ "grad_norm": 1.484375,
1768
+ "learning_rate": 6.459186531576772e-06,
1769
+ "loss": 0.8902,
1770
+ "step": 2470
1771
+ },
1772
+ {
1773
+ "epoch": 4.200719881431294,
1774
+ "grad_norm": 1.640625,
1775
+ "learning_rate": 6.427717347372523e-06,
1776
+ "loss": 0.8175,
1777
+ "step": 2480
1778
+ },
1779
+ {
1780
+ "epoch": 4.217658268049968,
1781
+ "grad_norm": 1.7109375,
1782
+ "learning_rate": 6.396186465840152e-06,
1783
+ "loss": 0.8717,
1784
+ "step": 2490
1785
+ },
1786
+ {
1787
+ "epoch": 4.234596654668643,
1788
+ "grad_norm": 1.5234375,
1789
+ "learning_rate": 6.364595249554084e-06,
1790
+ "loss": 0.8815,
1791
+ "step": 2500
1792
+ },
1793
+ {
1794
+ "epoch": 4.234596654668643,
1795
+ "eval_loss": 1.09398353099823,
1796
+ "eval_runtime": 20.9341,
1797
+ "eval_samples_per_second": 25.079,
1798
+ "eval_steps_per_second": 25.079,
1799
+ "step": 2500
1800
+ },
1801
+ {
1802
+ "epoch": 4.251535041287317,
1803
+ "grad_norm": 1.4296875,
1804
+ "learning_rate": 6.332945063696049e-06,
1805
+ "loss": 0.8658,
1806
+ "step": 2510
1807
+ },
1808
+ {
1809
+ "epoch": 4.268473427905992,
1810
+ "grad_norm": 1.3828125,
1811
+ "learning_rate": 6.3012372759960825e-06,
1812
+ "loss": 0.8465,
1813
+ "step": 2520
1814
+ },
1815
+ {
1816
+ "epoch": 4.285411814524666,
1817
+ "grad_norm": 1.5234375,
1818
+ "learning_rate": 6.26947325667343e-06,
1819
+ "loss": 0.8707,
1820
+ "step": 2530
1821
+ },
1822
+ {
1823
+ "epoch": 4.302350201143341,
1824
+ "grad_norm": 1.4140625,
1825
+ "learning_rate": 6.237654378377324e-06,
1826
+ "loss": 0.8921,
1827
+ "step": 2540
1828
+ },
1829
+ {
1830
+ "epoch": 4.319288587762015,
1831
+ "grad_norm": 1.5390625,
1832
+ "learning_rate": 6.2057820161276715e-06,
1833
+ "loss": 0.8703,
1834
+ "step": 2550
1835
+ },
1836
+ {
1837
+ "epoch": 4.33622697438069,
1838
+ "grad_norm": 1.2734375,
1839
+ "learning_rate": 6.173857547255634e-06,
1840
+ "loss": 0.8467,
1841
+ "step": 2560
1842
+ },
1843
+ {
1844
+ "epoch": 4.353165360999364,
1845
+ "grad_norm": 1.578125,
1846
+ "learning_rate": 6.141882351344106e-06,
1847
+ "loss": 0.8581,
1848
+ "step": 2570
1849
+ },
1850
+ {
1851
+ "epoch": 4.37010374761804,
1852
+ "grad_norm": 1.4609375,
1853
+ "learning_rate": 6.1098578101680986e-06,
1854
+ "loss": 0.8617,
1855
+ "step": 2580
1856
+ },
1857
+ {
1858
+ "epoch": 4.387042134236714,
1859
+ "grad_norm": 1.3046875,
1860
+ "learning_rate": 6.077785307635027e-06,
1861
+ "loss": 0.8082,
1862
+ "step": 2590
1863
+ },
1864
+ {
1865
+ "epoch": 4.403980520855389,
1866
+ "grad_norm": 1.34375,
1867
+ "learning_rate": 6.045666229724909e-06,
1868
+ "loss": 0.8048,
1869
+ "step": 2600
1870
+ },
1871
+ {
1872
+ "epoch": 4.420918907474063,
1873
+ "grad_norm": 1.4453125,
1874
+ "learning_rate": 6.013501964430468e-06,
1875
+ "loss": 0.8537,
1876
+ "step": 2610
1877
+ },
1878
+ {
1879
+ "epoch": 4.437857294092738,
1880
+ "grad_norm": 1.3359375,
1881
+ "learning_rate": 5.981293901697153e-06,
1882
+ "loss": 0.8683,
1883
+ "step": 2620
1884
+ },
1885
+ {
1886
+ "epoch": 4.454795680711412,
1887
+ "grad_norm": 1.1953125,
1888
+ "learning_rate": 5.9490434333630735e-06,
1889
+ "loss": 0.8599,
1890
+ "step": 2630
1891
+ },
1892
+ {
1893
+ "epoch": 4.471734067330087,
1894
+ "grad_norm": 1.3203125,
1895
+ "learning_rate": 5.916751953098854e-06,
1896
+ "loss": 0.8811,
1897
+ "step": 2640
1898
+ },
1899
+ {
1900
+ "epoch": 4.4886724539487615,
1901
+ "grad_norm": 1.21875,
1902
+ "learning_rate": 5.884420856347406e-06,
1903
+ "loss": 0.8891,
1904
+ "step": 2650
1905
+ },
1906
+ {
1907
+ "epoch": 4.505610840567436,
1908
+ "grad_norm": 1.3515625,
1909
+ "learning_rate": 5.852051540263628e-06,
1910
+ "loss": 0.8634,
1911
+ "step": 2660
1912
+ },
1913
+ {
1914
+ "epoch": 4.5225492271861105,
1915
+ "grad_norm": 1.28125,
1916
+ "learning_rate": 5.819645403654027e-06,
1917
+ "loss": 0.842,
1918
+ "step": 2670
1919
+ },
1920
+ {
1921
+ "epoch": 4.539487613804785,
1922
+ "grad_norm": 1.6484375,
1923
+ "learning_rate": 5.787203846916273e-06,
1924
+ "loss": 0.8485,
1925
+ "step": 2680
1926
+ },
1927
+ {
1928
+ "epoch": 4.55642600042346,
1929
+ "grad_norm": 1.265625,
1930
+ "learning_rate": 5.754728271978675e-06,
1931
+ "loss": 0.883,
1932
+ "step": 2690
1933
+ },
1934
+ {
1935
+ "epoch": 4.573364387042134,
1936
+ "grad_norm": 1.2265625,
1937
+ "learning_rate": 5.722220082239608e-06,
1938
+ "loss": 0.8457,
1939
+ "step": 2700
1940
+ },
1941
+ {
1942
+ "epoch": 4.590302773660809,
1943
+ "grad_norm": 1.1640625,
1944
+ "learning_rate": 5.689680682506861e-06,
1945
+ "loss": 0.8999,
1946
+ "step": 2710
1947
+ },
1948
+ {
1949
+ "epoch": 4.607241160279483,
1950
+ "grad_norm": 1.171875,
1951
+ "learning_rate": 5.657111478936926e-06,
1952
+ "loss": 0.8391,
1953
+ "step": 2720
1954
+ },
1955
+ {
1956
+ "epoch": 4.624179546898158,
1957
+ "grad_norm": 1.2265625,
1958
+ "learning_rate": 5.6245138789742444e-06,
1959
+ "loss": 0.8313,
1960
+ "step": 2730
1961
+ },
1962
+ {
1963
+ "epoch": 4.641117933516832,
1964
+ "grad_norm": 1.1640625,
1965
+ "learning_rate": 5.591889291290373e-06,
1966
+ "loss": 0.8709,
1967
+ "step": 2740
1968
+ },
1969
+ {
1970
+ "epoch": 4.658056320135507,
1971
+ "grad_norm": 0.9921875,
1972
+ "learning_rate": 5.559239125723119e-06,
1973
+ "loss": 0.8507,
1974
+ "step": 2750
1975
+ },
1976
+ {
1977
+ "epoch": 4.674994706754182,
1978
+ "grad_norm": 0.96484375,
1979
+ "learning_rate": 5.5265647932156066e-06,
1980
+ "loss": 0.9057,
1981
+ "step": 2760
1982
+ },
1983
+ {
1984
+ "epoch": 4.691933093372857,
1985
+ "grad_norm": 1.1171875,
1986
+ "learning_rate": 5.493867705755312e-06,
1987
+ "loss": 0.8386,
1988
+ "step": 2770
1989
+ },
1990
+ {
1991
+ "epoch": 4.708871479991531,
1992
+ "grad_norm": 1.0,
1993
+ "learning_rate": 5.461149276313046e-06,
1994
+ "loss": 0.9338,
1995
+ "step": 2780
1996
+ },
1997
+ {
1998
+ "epoch": 4.725809866610206,
1999
+ "grad_norm": 1.0234375,
2000
+ "learning_rate": 5.428410918781885e-06,
2001
+ "loss": 0.8176,
2002
+ "step": 2790
2003
+ },
2004
+ {
2005
+ "epoch": 4.74274825322888,
2006
+ "grad_norm": 1.046875,
2007
+ "learning_rate": 5.395654047916083e-06,
2008
+ "loss": 0.8609,
2009
+ "step": 2800
2010
+ },
2011
+ {
2012
+ "epoch": 4.759686639847555,
2013
+ "grad_norm": 1.09375,
2014
+ "learning_rate": 5.362880079269921e-06,
2015
+ "loss": 0.8494,
2016
+ "step": 2810
2017
+ },
2018
+ {
2019
+ "epoch": 4.776625026466229,
2020
+ "grad_norm": 1.1953125,
2021
+ "learning_rate": 5.330090429136553e-06,
2022
+ "loss": 0.8254,
2023
+ "step": 2820
2024
+ },
2025
+ {
2026
+ "epoch": 4.793563413084904,
2027
+ "grad_norm": 1.2890625,
2028
+ "learning_rate": 5.297286514486785e-06,
2029
+ "loss": 0.8689,
2030
+ "step": 2830
2031
+ },
2032
+ {
2033
+ "epoch": 4.810501799703578,
2034
+ "grad_norm": 1.125,
2035
+ "learning_rate": 5.26446975290785e-06,
2036
+ "loss": 0.8483,
2037
+ "step": 2840
2038
+ },
2039
+ {
2040
+ "epoch": 4.827440186322253,
2041
+ "grad_norm": 0.98046875,
2042
+ "learning_rate": 5.23164156254215e-06,
2043
+ "loss": 0.8436,
2044
+ "step": 2850
2045
+ },
2046
+ {
2047
+ "epoch": 4.844378572940927,
2048
+ "grad_norm": 0.91796875,
2049
+ "learning_rate": 5.19880336202597e-06,
2050
+ "loss": 0.8584,
2051
+ "step": 2860
2052
+ },
2053
+ {
2054
+ "epoch": 4.861316959559602,
2055
+ "grad_norm": 1.2265625,
2056
+ "learning_rate": 5.165956570428173e-06,
2057
+ "loss": 0.8122,
2058
+ "step": 2870
2059
+ },
2060
+ {
2061
+ "epoch": 4.8782553461782765,
2062
+ "grad_norm": 1.0703125,
2063
+ "learning_rate": 5.133102607188875e-06,
2064
+ "loss": 0.8705,
2065
+ "step": 2880
2066
+ },
2067
+ {
2068
+ "epoch": 4.895193732796951,
2069
+ "grad_norm": 1.34375,
2070
+ "learning_rate": 5.100242892058108e-06,
2071
+ "loss": 0.8788,
2072
+ "step": 2890
2073
+ },
2074
+ {
2075
+ "epoch": 4.9121321194156256,
2076
+ "grad_norm": 1.015625,
2077
+ "learning_rate": 5.067378845034468e-06,
2078
+ "loss": 0.8663,
2079
+ "step": 2900
2080
+ },
2081
+ {
2082
+ "epoch": 4.9290705060343,
2083
+ "grad_norm": 1.046875,
2084
+ "learning_rate": 5.034511886303746e-06,
2085
+ "loss": 0.8706,
2086
+ "step": 2910
2087
+ },
2088
+ {
2089
+ "epoch": 4.946008892652975,
2090
+ "grad_norm": 1.1171875,
2091
+ "learning_rate": 5.00164343617756e-06,
2092
+ "loss": 0.845,
2093
+ "step": 2920
2094
+ },
2095
+ {
2096
+ "epoch": 4.962947279271649,
2097
+ "grad_norm": 1.0078125,
2098
+ "learning_rate": 4.968774915031982e-06,
2099
+ "loss": 0.8165,
2100
+ "step": 2930
2101
+ },
2102
+ {
2103
+ "epoch": 4.979885665890324,
2104
+ "grad_norm": 1.3125,
2105
+ "learning_rate": 4.9359077432461455e-06,
2106
+ "loss": 0.8719,
2107
+ "step": 2940
2108
+ },
2109
+ {
2110
+ "epoch": 4.996824052508998,
2111
+ "grad_norm": 0.88671875,
2112
+ "learning_rate": 4.903043341140879e-06,
2113
+ "loss": 0.8579,
2114
+ "step": 2950
2115
+ },
2116
+ {
2117
+ "epoch": 5.013762439127673,
2118
+ "grad_norm": 0.921875,
2119
+ "learning_rate": 4.870183128917318e-06,
2120
+ "loss": 0.7986,
2121
+ "step": 2960
2122
+ },
2123
+ {
2124
+ "epoch": 5.030700825746347,
2125
+ "grad_norm": 1.140625,
2126
+ "learning_rate": 4.837328526595539e-06,
2127
+ "loss": 0.8119,
2128
+ "step": 2970
2129
+ },
2130
+ {
2131
+ "epoch": 5.047639212365023,
2132
+ "grad_norm": 0.97265625,
2133
+ "learning_rate": 4.804480953953193e-06,
2134
+ "loss": 0.8013,
2135
+ "step": 2980
2136
+ },
2137
+ {
2138
+ "epoch": 5.064577598983697,
2139
+ "grad_norm": 0.9296875,
2140
+ "learning_rate": 4.771641830464146e-06,
2141
+ "loss": 0.7954,
2142
+ "step": 2990
2143
+ },
2144
+ {
2145
+ "epoch": 5.081515985602372,
2146
+ "grad_norm": 1.046875,
2147
+ "learning_rate": 4.738812575237148e-06,
2148
+ "loss": 0.8159,
2149
+ "step": 3000
2150
+ },
2151
+ {
2152
+ "epoch": 5.081515985602372,
2153
+ "eval_loss": 1.0747902393341064,
2154
+ "eval_runtime": 20.9737,
2155
+ "eval_samples_per_second": 25.031,
2156
+ "eval_steps_per_second": 25.031,
2157
+ "step": 3000
2158
+ },
2159
+ {
2160
+ "epoch": 5.098454372221046,
2161
+ "grad_norm": 1.0625,
2162
+ "learning_rate": 4.705994606954497e-06,
2163
+ "loss": 0.7888,
2164
+ "step": 3010
2165
+ },
2166
+ {
2167
+ "epoch": 5.115392758839721,
2168
+ "grad_norm": 1.09375,
2169
+ "learning_rate": 4.673189343810747e-06,
2170
+ "loss": 0.8088,
2171
+ "step": 3020
2172
+ },
2173
+ {
2174
+ "epoch": 5.132331145458395,
2175
+ "grad_norm": 1.0,
2176
+ "learning_rate": 4.640398203451402e-06,
2177
+ "loss": 0.7762,
2178
+ "step": 3030
2179
+ },
2180
+ {
2181
+ "epoch": 5.14926953207707,
2182
+ "grad_norm": 1.078125,
2183
+ "learning_rate": 4.607622602911668e-06,
2184
+ "loss": 0.8108,
2185
+ "step": 3040
2186
+ },
2187
+ {
2188
+ "epoch": 5.166207918695744,
2189
+ "grad_norm": 1.1171875,
2190
+ "learning_rate": 4.574863958555215e-06,
2191
+ "loss": 0.7981,
2192
+ "step": 3050
2193
+ },
2194
+ {
2195
+ "epoch": 5.183146305314419,
2196
+ "grad_norm": 1.1953125,
2197
+ "learning_rate": 4.542123686012969e-06,
2198
+ "loss": 0.8295,
2199
+ "step": 3060
2200
+ },
2201
+ {
2202
+ "epoch": 5.200084691933093,
2203
+ "grad_norm": 1.1875,
2204
+ "learning_rate": 4.509403200121936e-06,
2205
+ "loss": 0.7986,
2206
+ "step": 3070
2207
+ },
2208
+ {
2209
+ "epoch": 5.217023078551768,
2210
+ "grad_norm": 1.1875,
2211
+ "learning_rate": 4.47670391486406e-06,
2212
+ "loss": 0.792,
2213
+ "step": 3080
2214
+ },
2215
+ {
2216
+ "epoch": 5.2339614651704425,
2217
+ "grad_norm": 1.1484375,
2218
+ "learning_rate": 4.44402724330513e-06,
2219
+ "loss": 0.8072,
2220
+ "step": 3090
2221
+ },
2222
+ {
2223
+ "epoch": 5.250899851789117,
2224
+ "grad_norm": 1.3203125,
2225
+ "learning_rate": 4.4113745975337e-06,
2226
+ "loss": 0.7877,
2227
+ "step": 3100
2228
+ },
2229
+ {
2230
+ "epoch": 5.2678382384077915,
2231
+ "grad_norm": 1.4921875,
2232
+ "learning_rate": 4.378747388600075e-06,
2233
+ "loss": 0.7823,
2234
+ "step": 3110
2235
+ },
2236
+ {
2237
+ "epoch": 5.284776625026466,
2238
+ "grad_norm": 1.40625,
2239
+ "learning_rate": 4.346147026455334e-06,
2240
+ "loss": 0.7957,
2241
+ "step": 3120
2242
+ },
2243
+ {
2244
+ "epoch": 5.301715011645141,
2245
+ "grad_norm": 1.390625,
2246
+ "learning_rate": 4.313574919890402e-06,
2247
+ "loss": 0.7562,
2248
+ "step": 3130
2249
+ },
2250
+ {
2251
+ "epoch": 5.318653398263815,
2252
+ "grad_norm": 1.3671875,
2253
+ "learning_rate": 4.281032476475165e-06,
2254
+ "loss": 0.7981,
2255
+ "step": 3140
2256
+ },
2257
+ {
2258
+ "epoch": 5.33559178488249,
2259
+ "grad_norm": 2.265625,
2260
+ "learning_rate": 4.248521102497649e-06,
2261
+ "loss": 0.7806,
2262
+ "step": 3150
2263
+ },
2264
+ {
2265
+ "epoch": 5.352530171501164,
2266
+ "grad_norm": 2.578125,
2267
+ "learning_rate": 4.216042202903246e-06,
2268
+ "loss": 0.848,
2269
+ "step": 3160
2270
+ },
2271
+ {
2272
+ "epoch": 5.369468558119839,
2273
+ "grad_norm": 2.171875,
2274
+ "learning_rate": 4.183597181234001e-06,
2275
+ "loss": 0.7903,
2276
+ "step": 3170
2277
+ },
2278
+ {
2279
+ "epoch": 5.386406944738514,
2280
+ "grad_norm": 2.515625,
2281
+ "learning_rate": 4.151187439567961e-06,
2282
+ "loss": 0.7914,
2283
+ "step": 3180
2284
+ },
2285
+ {
2286
+ "epoch": 5.403345331357189,
2287
+ "grad_norm": 2.25,
2288
+ "learning_rate": 4.118814378458582e-06,
2289
+ "loss": 0.7983,
2290
+ "step": 3190
2291
+ },
2292
+ {
2293
+ "epoch": 5.420283717975863,
2294
+ "grad_norm": 3.09375,
2295
+ "learning_rate": 4.086479396874206e-06,
2296
+ "loss": 0.7606,
2297
+ "step": 3200
2298
+ },
2299
+ {
2300
+ "epoch": 5.437222104594538,
2301
+ "grad_norm": 2.828125,
2302
+ "learning_rate": 4.054183892137611e-06,
2303
+ "loss": 0.7947,
2304
+ "step": 3210
2305
+ },
2306
+ {
2307
+ "epoch": 5.454160491213212,
2308
+ "grad_norm": 4.375,
2309
+ "learning_rate": 4.021929259865624e-06,
2310
+ "loss": 0.7764,
2311
+ "step": 3220
2312
+ },
2313
+ {
2314
+ "epoch": 5.471098877831887,
2315
+ "grad_norm": 4.46875,
2316
+ "learning_rate": 3.989716893908807e-06,
2317
+ "loss": 0.7829,
2318
+ "step": 3230
2319
+ },
2320
+ {
2321
+ "epoch": 5.488037264450561,
2322
+ "grad_norm": 3.5625,
2323
+ "learning_rate": 3.9575481862912335e-06,
2324
+ "loss": 0.7811,
2325
+ "step": 3240
2326
+ },
2327
+ {
2328
+ "epoch": 5.504975651069236,
2329
+ "grad_norm": 8.125,
2330
+ "learning_rate": 3.925424527150321e-06,
2331
+ "loss": 0.804,
2332
+ "step": 3250
2333
+ },
2334
+ {
2335
+ "epoch": 5.52191403768791,
2336
+ "grad_norm": 7.96875,
2337
+ "learning_rate": 3.893347304676766e-06,
2338
+ "loss": 0.7975,
2339
+ "step": 3260
2340
+ },
2341
+ {
2342
+ "epoch": 5.538852424306585,
2343
+ "grad_norm": 7.6875,
2344
+ "learning_rate": 3.861317905054551e-06,
2345
+ "loss": 0.7812,
2346
+ "step": 3270
2347
+ },
2348
+ {
2349
+ "epoch": 5.555790810925259,
2350
+ "grad_norm": 8.0625,
2351
+ "learning_rate": 3.8293377124010476e-06,
2352
+ "loss": 0.8092,
2353
+ "step": 3280
2354
+ },
2355
+ {
2356
+ "epoch": 5.572729197543934,
2357
+ "grad_norm": 8.0625,
2358
+ "learning_rate": 3.797408108707193e-06,
2359
+ "loss": 0.8141,
2360
+ "step": 3290
2361
+ },
2362
+ {
2363
+ "epoch": 5.5896675841626084,
2364
+ "grad_norm": 2.125,
2365
+ "learning_rate": 3.7655304737777775e-06,
2366
+ "loss": 0.815,
2367
+ "step": 3300
2368
+ },
2369
+ {
2370
+ "epoch": 5.606605970781283,
2371
+ "grad_norm": 2.109375,
2372
+ "learning_rate": 3.733706185171819e-06,
2373
+ "loss": 0.7505,
2374
+ "step": 3310
2375
+ },
2376
+ {
2377
+ "epoch": 5.6235443573999575,
2378
+ "grad_norm": 1.96875,
2379
+ "learning_rate": 3.701936618143025e-06,
2380
+ "loss": 0.7535,
2381
+ "step": 3320
2382
+ },
2383
+ {
2384
+ "epoch": 5.640482744018632,
2385
+ "grad_norm": 2.46875,
2386
+ "learning_rate": 3.6702231455803662e-06,
2387
+ "loss": 0.7703,
2388
+ "step": 3330
2389
+ },
2390
+ {
2391
+ "epoch": 5.657421130637307,
2392
+ "grad_norm": 2.15625,
2393
+ "learning_rate": 3.6385671379487496e-06,
2394
+ "loss": 0.7493,
2395
+ "step": 3340
2396
+ },
2397
+ {
2398
+ "epoch": 5.674359517255981,
2399
+ "grad_norm": 1.875,
2400
+ "learning_rate": 3.606969963229798e-06,
2401
+ "loss": 0.8281,
2402
+ "step": 3350
2403
+ },
2404
+ {
2405
+ "epoch": 5.691297903874656,
2406
+ "grad_norm": 1.9140625,
2407
+ "learning_rate": 3.5754329868627256e-06,
2408
+ "loss": 0.8207,
2409
+ "step": 3360
2410
+ },
2411
+ {
2412
+ "epoch": 5.70823629049333,
2413
+ "grad_norm": 2.046875,
2414
+ "learning_rate": 3.5439575716853414e-06,
2415
+ "loss": 0.8263,
2416
+ "step": 3370
2417
+ },
2418
+ {
2419
+ "epoch": 5.725174677112005,
2420
+ "grad_norm": 2.015625,
2421
+ "learning_rate": 3.5125450778751453e-06,
2422
+ "loss": 0.8106,
2423
+ "step": 3380
2424
+ },
2425
+ {
2426
+ "epoch": 5.742113063730679,
2427
+ "grad_norm": 2.125,
2428
+ "learning_rate": 3.4811968628905646e-06,
2429
+ "loss": 0.7993,
2430
+ "step": 3390
2431
+ },
2432
+ {
2433
+ "epoch": 5.759051450349354,
2434
+ "grad_norm": 1.84375,
2435
+ "learning_rate": 3.4499142814122766e-06,
2436
+ "loss": 0.7784,
2437
+ "step": 3400
2438
+ },
2439
+ {
2440
+ "epoch": 5.775989836968029,
2441
+ "grad_norm": 1.7890625,
2442
+ "learning_rate": 3.418698685284676e-06,
2443
+ "loss": 0.7762,
2444
+ "step": 3410
2445
+ },
2446
+ {
2447
+ "epoch": 5.792928223586704,
2448
+ "grad_norm": 1.8984375,
2449
+ "learning_rate": 3.387551423457456e-06,
2450
+ "loss": 0.7905,
2451
+ "step": 3420
2452
+ },
2453
+ {
2454
+ "epoch": 5.809866610205378,
2455
+ "grad_norm": 1.9765625,
2456
+ "learning_rate": 3.356473841927313e-06,
2457
+ "loss": 0.8273,
2458
+ "step": 3430
2459
+ },
2460
+ {
2461
+ "epoch": 5.826804996824053,
2462
+ "grad_norm": 2.046875,
2463
+ "learning_rate": 3.3254672836797814e-06,
2464
+ "loss": 0.7962,
2465
+ "step": 3440
2466
+ },
2467
+ {
2468
+ "epoch": 5.843743383442727,
2469
+ "grad_norm": 2.03125,
2470
+ "learning_rate": 3.2945330886311964e-06,
2471
+ "loss": 0.8146,
2472
+ "step": 3450
2473
+ },
2474
+ {
2475
+ "epoch": 5.860681770061402,
2476
+ "grad_norm": 1.9765625,
2477
+ "learning_rate": 3.263672593570797e-06,
2478
+ "loss": 0.8032,
2479
+ "step": 3460
2480
+ },
2481
+ {
2482
+ "epoch": 5.877620156680076,
2483
+ "grad_norm": 1.84375,
2484
+ "learning_rate": 3.23288713210295e-06,
2485
+ "loss": 0.7997,
2486
+ "step": 3470
2487
+ },
2488
+ {
2489
+ "epoch": 5.894558543298751,
2490
+ "grad_norm": 1.8828125,
2491
+ "learning_rate": 3.2021780345895216e-06,
2492
+ "loss": 0.8009,
2493
+ "step": 3480
2494
+ },
2495
+ {
2496
+ "epoch": 5.911496929917425,
2497
+ "grad_norm": 1.953125,
2498
+ "learning_rate": 3.1715466280923924e-06,
2499
+ "loss": 0.8302,
2500
+ "step": 3490
2501
+ },
2502
+ {
2503
+ "epoch": 5.9284353165361,
2504
+ "grad_norm": 2.359375,
2505
+ "learning_rate": 3.1409942363161037e-06,
2506
+ "loss": 0.8317,
2507
+ "step": 3500
2508
+ },
2509
+ {
2510
+ "epoch": 5.9284353165361,
2511
+ "eval_loss": 1.0828534364700317,
2512
+ "eval_runtime": 21.0141,
2513
+ "eval_samples_per_second": 24.983,
2514
+ "eval_steps_per_second": 24.983,
2515
+ "step": 3500
2516
+ },
2517
+ {
2518
+ "epoch": 5.945373703154774,
2519
+ "grad_norm": 2.125,
2520
+ "learning_rate": 3.1105221795506584e-06,
2521
+ "loss": 0.8026,
2522
+ "step": 3510
2523
+ },
2524
+ {
2525
+ "epoch": 5.962312089773449,
2526
+ "grad_norm": 2.046875,
2527
+ "learning_rate": 3.080131774614464e-06,
2528
+ "loss": 0.8209,
2529
+ "step": 3520
2530
+ },
2531
+ {
2532
+ "epoch": 5.9792504763921235,
2533
+ "grad_norm": 1.8515625,
2534
+ "learning_rate": 3.049824334797431e-06,
2535
+ "loss": 0.8086,
2536
+ "step": 3530
2537
+ },
2538
+ {
2539
+ "epoch": 5.996188863010798,
2540
+ "grad_norm": 2.015625,
2541
+ "learning_rate": 3.019601169804216e-06,
2542
+ "loss": 0.7651,
2543
+ "step": 3540
2544
+ },
2545
+ {
2546
+ "epoch": 6.0131272496294725,
2547
+ "grad_norm": 1.703125,
2548
+ "learning_rate": 2.9894635856976268e-06,
2549
+ "loss": 0.7734,
2550
+ "step": 3550
2551
+ },
2552
+ {
2553
+ "epoch": 6.030065636248147,
2554
+ "grad_norm": 1.8671875,
2555
+ "learning_rate": 2.959412884842181e-06,
2556
+ "loss": 0.7799,
2557
+ "step": 3560
2558
+ },
2559
+ {
2560
+ "epoch": 6.047004022866822,
2561
+ "grad_norm": 1.921875,
2562
+ "learning_rate": 2.929450365847828e-06,
2563
+ "loss": 0.7448,
2564
+ "step": 3570
2565
+ },
2566
+ {
2567
+ "epoch": 6.063942409485496,
2568
+ "grad_norm": 2.0,
2569
+ "learning_rate": 2.899577323513829e-06,
2570
+ "loss": 0.7354,
2571
+ "step": 3580
2572
+ },
2573
+ {
2574
+ "epoch": 6.080880796104171,
2575
+ "grad_norm": 2.109375,
2576
+ "learning_rate": 2.8697950487728e-06,
2577
+ "loss": 0.7585,
2578
+ "step": 3590
2579
+ },
2580
+ {
2581
+ "epoch": 6.097819182722846,
2582
+ "grad_norm": 1.828125,
2583
+ "learning_rate": 2.8401048286349353e-06,
2584
+ "loss": 0.7635,
2585
+ "step": 3600
2586
+ },
2587
+ {
2588
+ "epoch": 6.114757569341521,
2589
+ "grad_norm": 1.84375,
2590
+ "learning_rate": 2.8105079461323818e-06,
2591
+ "loss": 0.7781,
2592
+ "step": 3610
2593
+ },
2594
+ {
2595
+ "epoch": 6.131695955960195,
2596
+ "grad_norm": 1.8359375,
2597
+ "learning_rate": 2.7810056802637995e-06,
2598
+ "loss": 0.7646,
2599
+ "step": 3620
2600
+ },
2601
+ {
2602
+ "epoch": 6.14863434257887,
2603
+ "grad_norm": 1.96875,
2604
+ "learning_rate": 2.751599305939082e-06,
2605
+ "loss": 0.7657,
2606
+ "step": 3630
2607
+ },
2608
+ {
2609
+ "epoch": 6.165572729197544,
2610
+ "grad_norm": 2.109375,
2611
+ "learning_rate": 2.7222900939242787e-06,
2612
+ "loss": 0.7932,
2613
+ "step": 3640
2614
+ },
2615
+ {
2616
+ "epoch": 6.182511115816219,
2617
+ "grad_norm": 2.203125,
2618
+ "learning_rate": 2.693079310786661e-06,
2619
+ "loss": 0.7611,
2620
+ "step": 3650
2621
+ },
2622
+ {
2623
+ "epoch": 6.199449502434893,
2624
+ "grad_norm": 2.1875,
2625
+ "learning_rate": 2.6639682188400017e-06,
2626
+ "loss": 0.7631,
2627
+ "step": 3660
2628
+ },
2629
+ {
2630
+ "epoch": 6.216387889053568,
2631
+ "grad_norm": 2.140625,
2632
+ "learning_rate": 2.6349580760900232e-06,
2633
+ "loss": 0.7784,
2634
+ "step": 3670
2635
+ },
2636
+ {
2637
+ "epoch": 6.233326275672242,
2638
+ "grad_norm": 2.234375,
2639
+ "learning_rate": 2.6060501361800333e-06,
2640
+ "loss": 0.7479,
2641
+ "step": 3680
2642
+ },
2643
+ {
2644
+ "epoch": 6.250264662290917,
2645
+ "grad_norm": 2.171875,
2646
+ "learning_rate": 2.57724564833675e-06,
2647
+ "loss": 0.7367,
2648
+ "step": 3690
2649
+ },
2650
+ {
2651
+ "epoch": 6.267203048909591,
2652
+ "grad_norm": 1.875,
2653
+ "learning_rate": 2.5485458573163114e-06,
2654
+ "loss": 0.7463,
2655
+ "step": 3700
2656
+ },
2657
+ {
2658
+ "epoch": 6.284141435528266,
2659
+ "grad_norm": 1.953125,
2660
+ "learning_rate": 2.519952003350499e-06,
2661
+ "loss": 0.7557,
2662
+ "step": 3710
2663
+ },
2664
+ {
2665
+ "epoch": 6.30107982214694,
2666
+ "grad_norm": 2.0,
2667
+ "learning_rate": 2.4914653220931283e-06,
2668
+ "loss": 0.8084,
2669
+ "step": 3720
2670
+ },
2671
+ {
2672
+ "epoch": 6.318018208765615,
2673
+ "grad_norm": 1.875,
2674
+ "learning_rate": 2.4630870445666576e-06,
2675
+ "loss": 0.7493,
2676
+ "step": 3730
2677
+ },
2678
+ {
2679
+ "epoch": 6.3349565953842895,
2680
+ "grad_norm": 2.15625,
2681
+ "learning_rate": 2.434818397108993e-06,
2682
+ "loss": 0.7959,
2683
+ "step": 3740
2684
+ },
2685
+ {
2686
+ "epoch": 6.351894982002964,
2687
+ "grad_norm": 2.21875,
2688
+ "learning_rate": 2.406660601320489e-06,
2689
+ "loss": 0.7245,
2690
+ "step": 3750
2691
+ },
2692
+ {
2693
+ "epoch": 6.3688333686216385,
2694
+ "grad_norm": 2.25,
2695
+ "learning_rate": 2.378614874011162e-06,
2696
+ "loss": 0.7637,
2697
+ "step": 3760
2698
+ },
2699
+ {
2700
+ "epoch": 6.385771755240313,
2701
+ "grad_norm": 2.15625,
2702
+ "learning_rate": 2.3506824271480987e-06,
2703
+ "loss": 0.7702,
2704
+ "step": 3770
2705
+ },
2706
+ {
2707
+ "epoch": 6.402710141858988,
2708
+ "grad_norm": 2.09375,
2709
+ "learning_rate": 2.322864467803097e-06,
2710
+ "loss": 0.7155,
2711
+ "step": 3780
2712
+ },
2713
+ {
2714
+ "epoch": 6.419648528477662,
2715
+ "grad_norm": 2.015625,
2716
+ "learning_rate": 2.2951621981004873e-06,
2717
+ "loss": 0.7925,
2718
+ "step": 3790
2719
+ },
2720
+ {
2721
+ "epoch": 6.436586915096337,
2722
+ "grad_norm": 1.96875,
2723
+ "learning_rate": 2.2675768151651993e-06,
2724
+ "loss": 0.7901,
2725
+ "step": 3800
2726
+ },
2727
+ {
2728
+ "epoch": 6.453525301715012,
2729
+ "grad_norm": 2.09375,
2730
+ "learning_rate": 2.240109511071014e-06,
2731
+ "loss": 0.729,
2732
+ "step": 3810
2733
+ },
2734
+ {
2735
+ "epoch": 6.470463688333687,
2736
+ "grad_norm": 2.109375,
2737
+ "learning_rate": 2.2127614727890627e-06,
2738
+ "loss": 0.7481,
2739
+ "step": 3820
2740
+ },
2741
+ {
2742
+ "epoch": 6.487402074952361,
2743
+ "grad_norm": 1.90625,
2744
+ "learning_rate": 2.1855338821365302e-06,
2745
+ "loss": 0.7148,
2746
+ "step": 3830
2747
+ },
2748
+ {
2749
+ "epoch": 6.504340461571036,
2750
+ "grad_norm": 1.8125,
2751
+ "learning_rate": 2.158427915725573e-06,
2752
+ "loss": 0.7748,
2753
+ "step": 3840
2754
+ },
2755
+ {
2756
+ "epoch": 6.52127884818971,
2757
+ "grad_norm": 2.125,
2758
+ "learning_rate": 2.131444744912492e-06,
2759
+ "loss": 0.7601,
2760
+ "step": 3850
2761
+ },
2762
+ {
2763
+ "epoch": 6.538217234808385,
2764
+ "grad_norm": 2.0625,
2765
+ "learning_rate": 2.1045855357470944e-06,
2766
+ "loss": 0.7397,
2767
+ "step": 3860
2768
+ },
2769
+ {
2770
+ "epoch": 6.555155621427059,
2771
+ "grad_norm": 2.578125,
2772
+ "learning_rate": 2.0778514489223207e-06,
2773
+ "loss": 0.7072,
2774
+ "step": 3870
2775
+ },
2776
+ {
2777
+ "epoch": 6.572094008045734,
2778
+ "grad_norm": 2.21875,
2779
+ "learning_rate": 2.051243639724071e-06,
2780
+ "loss": 0.7204,
2781
+ "step": 3880
2782
+ },
2783
+ {
2784
+ "epoch": 6.589032394664408,
2785
+ "grad_norm": 2.15625,
2786
+ "learning_rate": 2.024763257981296e-06,
2787
+ "loss": 0.7579,
2788
+ "step": 3890
2789
+ },
2790
+ {
2791
+ "epoch": 6.605970781283083,
2792
+ "grad_norm": 1.9765625,
2793
+ "learning_rate": 1.9984114480162976e-06,
2794
+ "loss": 0.7411,
2795
+ "step": 3900
2796
+ },
2797
+ {
2798
+ "epoch": 6.622909167901757,
2799
+ "grad_norm": 2.03125,
2800
+ "learning_rate": 1.9721893485952785e-06,
2801
+ "loss": 0.7513,
2802
+ "step": 3910
2803
+ },
2804
+ {
2805
+ "epoch": 6.639847554520432,
2806
+ "grad_norm": 2.0625,
2807
+ "learning_rate": 1.9460980928791407e-06,
2808
+ "loss": 0.7629,
2809
+ "step": 3920
2810
+ },
2811
+ {
2812
+ "epoch": 6.656785941139106,
2813
+ "grad_norm": 1.96875,
2814
+ "learning_rate": 1.9201388083745036e-06,
2815
+ "loss": 0.767,
2816
+ "step": 3930
2817
+ },
2818
+ {
2819
+ "epoch": 6.673724327757781,
2820
+ "grad_norm": 2.0625,
2821
+ "learning_rate": 1.8943126168849947e-06,
2822
+ "loss": 0.731,
2823
+ "step": 3940
2824
+ },
2825
+ {
2826
+ "epoch": 6.690662714376455,
2827
+ "grad_norm": 1.78125,
2828
+ "learning_rate": 1.868620634462756e-06,
2829
+ "loss": 0.7335,
2830
+ "step": 3950
2831
+ },
2832
+ {
2833
+ "epoch": 6.70760110099513,
2834
+ "grad_norm": 2.109375,
2835
+ "learning_rate": 1.8430639713602317e-06,
2836
+ "loss": 0.7791,
2837
+ "step": 3960
2838
+ },
2839
+ {
2840
+ "epoch": 6.7245394876138045,
2841
+ "grad_norm": 1.9921875,
2842
+ "learning_rate": 1.8176437319821789e-06,
2843
+ "loss": 0.7231,
2844
+ "step": 3970
2845
+ },
2846
+ {
2847
+ "epoch": 6.741477874232479,
2848
+ "grad_norm": 1.9375,
2849
+ "learning_rate": 1.79236101483794e-06,
2850
+ "loss": 0.7355,
2851
+ "step": 3980
2852
+ },
2853
+ {
2854
+ "epoch": 6.7584162608511535,
2855
+ "grad_norm": 1.734375,
2856
+ "learning_rate": 1.7672169124939843e-06,
2857
+ "loss": 0.7737,
2858
+ "step": 3990
2859
+ },
2860
+ {
2861
+ "epoch": 6.775354647469829,
2862
+ "grad_norm": 1.96875,
2863
+ "learning_rate": 1.7422125115266785e-06,
2864
+ "loss": 0.7269,
2865
+ "step": 4000
2866
+ },
2867
+ {
2868
+ "epoch": 6.775354647469829,
2869
+ "eval_loss": 1.0812190771102905,
2870
+ "eval_runtime": 21.7625,
2871
+ "eval_samples_per_second": 24.124,
2872
+ "eval_steps_per_second": 24.124,
2873
+ "step": 4000
2874
+ },
2875
+ {
2876
+ "epoch": 6.7922930340885035,
2877
+ "grad_norm": 1.7890625,
2878
+ "learning_rate": 1.7173488924753451e-06,
2879
+ "loss": 0.7756,
2880
+ "step": 4010
2881
+ },
2882
+ {
2883
+ "epoch": 6.809231420707178,
2884
+ "grad_norm": 1.6953125,
2885
+ "learning_rate": 1.6926271297955549e-06,
2886
+ "loss": 0.7597,
2887
+ "step": 4020
2888
+ },
2889
+ {
2890
+ "epoch": 6.8261698073258525,
2891
+ "grad_norm": 1.90625,
2892
+ "learning_rate": 1.668048291812709e-06,
2893
+ "loss": 0.7463,
2894
+ "step": 4030
2895
+ },
2896
+ {
2897
+ "epoch": 6.843108193944527,
2898
+ "grad_norm": 3.25,
2899
+ "learning_rate": 1.6436134406758635e-06,
2900
+ "loss": 0.7202,
2901
+ "step": 4040
2902
+ },
2903
+ {
2904
+ "epoch": 6.860046580563202,
2905
+ "grad_norm": 1.6875,
2906
+ "learning_rate": 1.6193236323118283e-06,
2907
+ "loss": 0.7765,
2908
+ "step": 4050
2909
+ },
2910
+ {
2911
+ "epoch": 6.876984967181876,
2912
+ "grad_norm": 1.84375,
2913
+ "learning_rate": 1.5951799163795461e-06,
2914
+ "loss": 0.7552,
2915
+ "step": 4060
2916
+ },
2917
+ {
2918
+ "epoch": 6.893923353800551,
2919
+ "grad_norm": 1.6484375,
2920
+ "learning_rate": 1.5711833362247204e-06,
2921
+ "loss": 0.7565,
2922
+ "step": 4070
2923
+ },
2924
+ {
2925
+ "epoch": 6.910861740419225,
2926
+ "grad_norm": 1.7265625,
2927
+ "learning_rate": 1.547334928834739e-06,
2928
+ "loss": 0.7342,
2929
+ "step": 4080
2930
+ },
2931
+ {
2932
+ "epoch": 6.9278001270379,
2933
+ "grad_norm": 1.578125,
2934
+ "learning_rate": 1.523635724793852e-06,
2935
+ "loss": 0.7602,
2936
+ "step": 4090
2937
+ },
2938
+ {
2939
+ "epoch": 6.944738513656574,
2940
+ "grad_norm": 1.6015625,
2941
+ "learning_rate": 1.5000867482386478e-06,
2942
+ "loss": 0.7839,
2943
+ "step": 4100
2944
+ },
2945
+ {
2946
+ "epoch": 6.961676900275249,
2947
+ "grad_norm": 1.6171875,
2948
+ "learning_rate": 1.4766890168137816e-06,
2949
+ "loss": 0.7512,
2950
+ "step": 4110
2951
+ },
2952
+ {
2953
+ "epoch": 6.978615286893923,
2954
+ "grad_norm": 1.6484375,
2955
+ "learning_rate": 1.4534435416280135e-06,
2956
+ "loss": 0.7715,
2957
+ "step": 4120
2958
+ },
2959
+ {
2960
+ "epoch": 6.995553673512598,
2961
+ "grad_norm": 1.546875,
2962
+ "learning_rate": 1.4303513272105057e-06,
2963
+ "loss": 0.7924,
2964
+ "step": 4130
2965
+ },
2966
+ {
2967
+ "epoch": 7.012492060131272,
2968
+ "grad_norm": 1.4453125,
2969
+ "learning_rate": 1.4074133714674116e-06,
2970
+ "loss": 0.7509,
2971
+ "step": 4140
2972
+ },
2973
+ {
2974
+ "epoch": 7.029430446749947,
2975
+ "grad_norm": 1.3984375,
2976
+ "learning_rate": 1.3846306656387603e-06,
2977
+ "loss": 0.7349,
2978
+ "step": 4150
2979
+ },
2980
+ {
2981
+ "epoch": 7.046368833368621,
2982
+ "grad_norm": 1.4765625,
2983
+ "learning_rate": 1.3620041942556127e-06,
2984
+ "loss": 0.7525,
2985
+ "step": 4160
2986
+ },
2987
+ {
2988
+ "epoch": 7.063307219987296,
2989
+ "grad_norm": 1.34375,
2990
+ "learning_rate": 1.339534935097524e-06,
2991
+ "loss": 0.7515,
2992
+ "step": 4170
2993
+ },
2994
+ {
2995
+ "epoch": 7.0802456066059705,
2996
+ "grad_norm": 1.4296875,
2997
+ "learning_rate": 1.3172238591502794e-06,
2998
+ "loss": 0.7433,
2999
+ "step": 4180
3000
+ },
3001
+ {
3002
+ "epoch": 7.097183993224645,
3003
+ "grad_norm": 1.265625,
3004
+ "learning_rate": 1.2950719305639464e-06,
3005
+ "loss": 0.7416,
3006
+ "step": 4190
3007
+ },
3008
+ {
3009
+ "epoch": 7.1141223798433195,
3010
+ "grad_norm": 1.3984375,
3011
+ "learning_rate": 1.2730801066112024e-06,
3012
+ "loss": 0.7115,
3013
+ "step": 4200
3014
+ },
3015
+ {
3016
+ "epoch": 7.131060766461994,
3017
+ "grad_norm": 1.3203125,
3018
+ "learning_rate": 1.251249337645965e-06,
3019
+ "loss": 0.6892,
3020
+ "step": 4210
3021
+ },
3022
+ {
3023
+ "epoch": 7.1479991530806695,
3024
+ "grad_norm": 1.3125,
3025
+ "learning_rate": 1.229580567062334e-06,
3026
+ "loss": 0.704,
3027
+ "step": 4220
3028
+ },
3029
+ {
3030
+ "epoch": 7.164937539699344,
3031
+ "grad_norm": 1.3203125,
3032
+ "learning_rate": 1.2080747312538082e-06,
3033
+ "loss": 0.7021,
3034
+ "step": 4230
3035
+ },
3036
+ {
3037
+ "epoch": 7.1818759263180185,
3038
+ "grad_norm": 1.3828125,
3039
+ "learning_rate": 1.1867327595728373e-06,
3040
+ "loss": 0.6669,
3041
+ "step": 4240
3042
+ },
3043
+ {
3044
+ "epoch": 7.198814312936693,
3045
+ "grad_norm": 1.2890625,
3046
+ "learning_rate": 1.1655555742906438e-06,
3047
+ "loss": 0.7433,
3048
+ "step": 4250
3049
+ },
3050
+ {
3051
+ "epoch": 7.215752699555368,
3052
+ "grad_norm": 1.3046875,
3053
+ "learning_rate": 1.1445440905573857e-06,
3054
+ "loss": 0.7294,
3055
+ "step": 4260
3056
+ },
3057
+ {
3058
+ "epoch": 7.232691086174042,
3059
+ "grad_norm": 1.359375,
3060
+ "learning_rate": 1.1236992163625933e-06,
3061
+ "loss": 0.7121,
3062
+ "step": 4270
3063
+ },
3064
+ {
3065
+ "epoch": 7.249629472792717,
3066
+ "grad_norm": 1.3046875,
3067
+ "learning_rate": 1.1030218524959375e-06,
3068
+ "loss": 0.6407,
3069
+ "step": 4280
3070
+ },
3071
+ {
3072
+ "epoch": 7.266567859411391,
3073
+ "grad_norm": 1.515625,
3074
+ "learning_rate": 1.082512892508309e-06,
3075
+ "loss": 0.7426,
3076
+ "step": 4290
3077
+ },
3078
+ {
3079
+ "epoch": 7.283506246030066,
3080
+ "grad_norm": 1.265625,
3081
+ "learning_rate": 1.062173222673194e-06,
3082
+ "loss": 0.7256,
3083
+ "step": 4300
3084
+ },
3085
+ {
3086
+ "epoch": 7.30044463264874,
3087
+ "grad_norm": 1.140625,
3088
+ "learning_rate": 1.0420037219483842e-06,
3089
+ "loss": 0.7149,
3090
+ "step": 4310
3091
+ },
3092
+ {
3093
+ "epoch": 7.317383019267415,
3094
+ "grad_norm": 1.171875,
3095
+ "learning_rate": 1.0220052619379844e-06,
3096
+ "loss": 0.7327,
3097
+ "step": 4320
3098
+ },
3099
+ {
3100
+ "epoch": 7.334321405886089,
3101
+ "grad_norm": 1.2734375,
3102
+ "learning_rate": 1.0021787068547568e-06,
3103
+ "loss": 0.7728,
3104
+ "step": 4330
3105
+ },
3106
+ {
3107
+ "epoch": 7.351259792504764,
3108
+ "grad_norm": 1.2890625,
3109
+ "learning_rate": 9.825249134827664e-07,
3110
+ "loss": 0.745,
3111
+ "step": 4340
3112
+ },
3113
+ {
3114
+ "epoch": 7.368198179123438,
3115
+ "grad_norm": 1.046875,
3116
+ "learning_rate": 9.630447311403623e-07,
3117
+ "loss": 0.7625,
3118
+ "step": 4350
3119
+ },
3120
+ {
3121
+ "epoch": 7.385136565742113,
3122
+ "grad_norm": 1.0703125,
3123
+ "learning_rate": 9.437390016434711e-07,
3124
+ "loss": 0.7297,
3125
+ "step": 4360
3126
+ },
3127
+ {
3128
+ "epoch": 7.402074952360787,
3129
+ "grad_norm": 1.1015625,
3130
+ "learning_rate": 9.246085592692183e-07,
3131
+ "loss": 0.6938,
3132
+ "step": 4370
3133
+ },
3134
+ {
3135
+ "epoch": 7.419013338979462,
3136
+ "grad_norm": 1.1015625,
3137
+ "learning_rate": 9.056542307198823e-07,
3138
+ "loss": 0.721,
3139
+ "step": 4380
3140
+ },
3141
+ {
3142
+ "epoch": 7.435951725598136,
3143
+ "grad_norm": 1.0703125,
3144
+ "learning_rate": 8.868768350871592e-07,
3145
+ "loss": 0.712,
3146
+ "step": 4390
3147
+ },
3148
+ {
3149
+ "epoch": 7.452890112216811,
3150
+ "grad_norm": 1.1640625,
3151
+ "learning_rate": 8.682771838167775e-07,
3152
+ "loss": 0.7684,
3153
+ "step": 4400
3154
+ },
3155
+ {
3156
+ "epoch": 7.469828498835486,
3157
+ "grad_norm": 1.109375,
3158
+ "learning_rate": 8.49856080673423e-07,
3159
+ "loss": 0.723,
3160
+ "step": 4410
3161
+ },
3162
+ {
3163
+ "epoch": 7.486766885454161,
3164
+ "grad_norm": 1.046875,
3165
+ "learning_rate": 8.316143217060129e-07,
3166
+ "loss": 0.7165,
3167
+ "step": 4420
3168
+ },
3169
+ {
3170
+ "epoch": 7.503705272072835,
3171
+ "grad_norm": 1.0625,
3172
+ "learning_rate": 8.135526952132877e-07,
3173
+ "loss": 0.7471,
3174
+ "step": 4430
3175
+ },
3176
+ {
3177
+ "epoch": 7.52064365869151,
3178
+ "grad_norm": 1.109375,
3179
+ "learning_rate": 7.956719817097491e-07,
3180
+ "loss": 0.7388,
3181
+ "step": 4440
3182
+ },
3183
+ {
3184
+ "epoch": 7.5375820453101845,
3185
+ "grad_norm": 1.0078125,
3186
+ "learning_rate": 7.779729538919351e-07,
3187
+ "loss": 0.7165,
3188
+ "step": 4450
3189
+ },
3190
+ {
3191
+ "epoch": 7.554520431928859,
3192
+ "grad_norm": 0.9609375,
3193
+ "learning_rate": 7.6045637660502e-07,
3194
+ "loss": 0.7349,
3195
+ "step": 4460
3196
+ },
3197
+ {
3198
+ "epoch": 7.5714588185475336,
3199
+ "grad_norm": 1.171875,
3200
+ "learning_rate": 7.4312300680977e-07,
3201
+ "loss": 0.6813,
3202
+ "step": 4470
3203
+ },
3204
+ {
3205
+ "epoch": 7.588397205166208,
3206
+ "grad_norm": 1.09375,
3207
+ "learning_rate": 7.259735935498297e-07,
3208
+ "loss": 0.7447,
3209
+ "step": 4480
3210
+ },
3211
+ {
3212
+ "epoch": 7.605335591784883,
3213
+ "grad_norm": 0.9609375,
3214
+ "learning_rate": 7.090088779193516e-07,
3215
+ "loss": 0.6976,
3216
+ "step": 4490
3217
+ },
3218
+ {
3219
+ "epoch": 7.622273978403557,
3220
+ "grad_norm": 0.98046875,
3221
+ "learning_rate": 6.922295930309691e-07,
3222
+ "loss": 0.7372,
3223
+ "step": 4500
3224
+ },
3225
+ {
3226
+ "epoch": 7.622273978403557,
3227
+ "eval_loss": 1.0816632509231567,
3228
+ "eval_runtime": 21.0317,
3229
+ "eval_samples_per_second": 24.962,
3230
+ "eval_steps_per_second": 24.962,
3231
+ "step": 4500
3232
+ },
3233
+ {
3234
+ "epoch": 7.639212365022232,
3235
+ "grad_norm": 1.078125,
3236
+ "learning_rate": 6.756364639841217e-07,
3237
+ "loss": 0.703,
3238
+ "step": 4510
3239
+ },
3240
+ {
3241
+ "epoch": 7.656150751640906,
3242
+ "grad_norm": 1.0390625,
3243
+ "learning_rate": 6.592302078337132e-07,
3244
+ "loss": 0.7121,
3245
+ "step": 4520
3246
+ },
3247
+ {
3248
+ "epoch": 7.673089138259581,
3249
+ "grad_norm": 1.0078125,
3250
+ "learning_rate": 6.430115335591291e-07,
3251
+ "loss": 0.7669,
3252
+ "step": 4530
3253
+ },
3254
+ {
3255
+ "epoch": 7.690027524878255,
3256
+ "grad_norm": 1.0234375,
3257
+ "learning_rate": 6.26981142033602e-07,
3258
+ "loss": 0.7015,
3259
+ "step": 4540
3260
+ },
3261
+ {
3262
+ "epoch": 7.70696591149693,
3263
+ "grad_norm": 1.0390625,
3264
+ "learning_rate": 6.111397259939128e-07,
3265
+ "loss": 0.736,
3266
+ "step": 4550
3267
+ },
3268
+ {
3269
+ "epoch": 7.723904298115604,
3270
+ "grad_norm": 1.0390625,
3271
+ "learning_rate": 5.954879700104732e-07,
3272
+ "loss": 0.7379,
3273
+ "step": 4560
3274
+ },
3275
+ {
3276
+ "epoch": 7.740842684734279,
3277
+ "grad_norm": 1.09375,
3278
+ "learning_rate": 5.800265504577202e-07,
3279
+ "loss": 0.7687,
3280
+ "step": 4570
3281
+ },
3282
+ {
3283
+ "epoch": 7.757781071352953,
3284
+ "grad_norm": 0.96875,
3285
+ "learning_rate": 5.647561354849079e-07,
3286
+ "loss": 0.7316,
3287
+ "step": 4580
3288
+ },
3289
+ {
3290
+ "epoch": 7.774719457971628,
3291
+ "grad_norm": 1.03125,
3292
+ "learning_rate": 5.496773849872183e-07,
3293
+ "loss": 0.7466,
3294
+ "step": 4590
3295
+ },
3296
+ {
3297
+ "epoch": 7.791657844590302,
3298
+ "grad_norm": 1.09375,
3299
+ "learning_rate": 5.347909505772569e-07,
3300
+ "loss": 0.734,
3301
+ "step": 4600
3302
+ },
3303
+ {
3304
+ "epoch": 7.808596231208977,
3305
+ "grad_norm": 1.0546875,
3306
+ "learning_rate": 5.200974755568849e-07,
3307
+ "loss": 0.7497,
3308
+ "step": 4610
3309
+ },
3310
+ {
3311
+ "epoch": 7.8255346178276515,
3312
+ "grad_norm": 1.046875,
3313
+ "learning_rate": 5.055975948894226e-07,
3314
+ "loss": 0.7562,
3315
+ "step": 4620
3316
+ },
3317
+ {
3318
+ "epoch": 7.842473004446326,
3319
+ "grad_norm": 1.125,
3320
+ "learning_rate": 4.912919351722151e-07,
3321
+ "loss": 0.7017,
3322
+ "step": 4630
3323
+ },
3324
+ {
3325
+ "epoch": 7.859411391065001,
3326
+ "grad_norm": 1.1328125,
3327
+ "learning_rate": 4.771811146095451e-07,
3328
+ "loss": 0.6976,
3329
+ "step": 4640
3330
+ },
3331
+ {
3332
+ "epoch": 7.876349777683676,
3333
+ "grad_norm": 1.046875,
3334
+ "learning_rate": 4.6326574298592666e-07,
3335
+ "loss": 0.6964,
3336
+ "step": 4650
3337
+ },
3338
+ {
3339
+ "epoch": 7.8932881643023505,
3340
+ "grad_norm": 1.203125,
3341
+ "learning_rate": 4.49546421639746e-07,
3342
+ "loss": 0.7239,
3343
+ "step": 4660
3344
+ },
3345
+ {
3346
+ "epoch": 7.910226550921025,
3347
+ "grad_norm": 1.0625,
3348
+ "learning_rate": 4.360237434372838e-07,
3349
+ "loss": 0.7632,
3350
+ "step": 4670
3351
+ },
3352
+ {
3353
+ "epoch": 7.9271649375396995,
3354
+ "grad_norm": 1.1640625,
3355
+ "learning_rate": 4.226982927470874e-07,
3356
+ "loss": 0.7184,
3357
+ "step": 4680
3358
+ },
3359
+ {
3360
+ "epoch": 7.944103324158374,
3361
+ "grad_norm": 1.1484375,
3362
+ "learning_rate": 4.0957064541472305e-07,
3363
+ "loss": 0.7238,
3364
+ "step": 4690
3365
+ },
3366
+ {
3367
+ "epoch": 7.961041710777049,
3368
+ "grad_norm": 1.421875,
3369
+ "learning_rate": 3.966413687378895e-07,
3370
+ "loss": 0.7361,
3371
+ "step": 4700
3372
+ },
3373
+ {
3374
+ "epoch": 7.977980097395723,
3375
+ "grad_norm": 1.390625,
3376
+ "learning_rate": 3.8391102144190175e-07,
3377
+ "loss": 0.723,
3378
+ "step": 4710
3379
+ },
3380
+ {
3381
+ "epoch": 7.994918484014398,
3382
+ "grad_norm": 1.4296875,
3383
+ "learning_rate": 3.7138015365554834e-07,
3384
+ "loss": 0.7064,
3385
+ "step": 4720
3386
+ },
3387
+ {
3388
+ "epoch": 8.011856870633073,
3389
+ "grad_norm": 1.3125,
3390
+ "learning_rate": 3.590493068873163e-07,
3391
+ "loss": 0.7317,
3392
+ "step": 4730
3393
+ },
3394
+ {
3395
+ "epoch": 8.028795257251748,
3396
+ "grad_norm": 1.3359375,
3397
+ "learning_rate": 3.4691901400199234e-07,
3398
+ "loss": 0.7102,
3399
+ "step": 4740
3400
+ },
3401
+ {
3402
+ "epoch": 8.045733643870422,
3403
+ "grad_norm": 2.4375,
3404
+ "learning_rate": 3.349897991976336e-07,
3405
+ "loss": 0.681,
3406
+ "step": 4750
3407
+ },
3408
+ {
3409
+ "epoch": 8.062672030489097,
3410
+ "grad_norm": 2.171875,
3411
+ "learning_rate": 3.232621779829176e-07,
3412
+ "loss": 0.6939,
3413
+ "step": 4760
3414
+ },
3415
+ {
3416
+ "epoch": 8.079610417107771,
3417
+ "grad_norm": 2.140625,
3418
+ "learning_rate": 3.1173665715486076e-07,
3419
+ "loss": 0.7276,
3420
+ "step": 4770
3421
+ },
3422
+ {
3423
+ "epoch": 8.096548803726446,
3424
+ "grad_norm": 2.09375,
3425
+ "learning_rate": 3.0041373477692315e-07,
3426
+ "loss": 0.6762,
3427
+ "step": 4780
3428
+ },
3429
+ {
3430
+ "epoch": 8.11348719034512,
3431
+ "grad_norm": 2.171875,
3432
+ "learning_rate": 2.8929390015748124e-07,
3433
+ "loss": 0.7547,
3434
+ "step": 4790
3435
+ },
3436
+ {
3437
+ "epoch": 8.130425576963795,
3438
+ "grad_norm": 3.71875,
3439
+ "learning_rate": 2.7837763382868253e-07,
3440
+ "loss": 0.716,
3441
+ "step": 4800
3442
+ },
3443
+ {
3444
+ "epoch": 8.14736396358247,
3445
+ "grad_norm": 3.15625,
3446
+ "learning_rate": 2.6766540752568514e-07,
3447
+ "loss": 0.7306,
3448
+ "step": 4810
3449
+ },
3450
+ {
3451
+ "epoch": 8.164302350201144,
3452
+ "grad_norm": 3.46875,
3453
+ "learning_rate": 2.5715768416626486e-07,
3454
+ "loss": 0.6856,
3455
+ "step": 4820
3456
+ },
3457
+ {
3458
+ "epoch": 8.181240736819818,
3459
+ "grad_norm": 3.859375,
3460
+ "learning_rate": 2.4685491783081715e-07,
3461
+ "loss": 0.6798,
3462
+ "step": 4830
3463
+ },
3464
+ {
3465
+ "epoch": 8.198179123438493,
3466
+ "grad_norm": 3.46875,
3467
+ "learning_rate": 2.3675755374272857e-07,
3468
+ "loss": 0.7652,
3469
+ "step": 4840
3470
+ },
3471
+ {
3472
+ "epoch": 8.215117510057167,
3473
+ "grad_norm": 8.0,
3474
+ "learning_rate": 2.268660282491436e-07,
3475
+ "loss": 0.6881,
3476
+ "step": 4850
3477
+ },
3478
+ {
3479
+ "epoch": 8.232055896675842,
3480
+ "grad_norm": 7.21875,
3481
+ "learning_rate": 2.1718076880210325e-07,
3482
+ "loss": 0.7532,
3483
+ "step": 4860
3484
+ },
3485
+ {
3486
+ "epoch": 8.248994283294516,
3487
+ "grad_norm": 7.0625,
3488
+ "learning_rate": 2.0770219394007362e-07,
3489
+ "loss": 0.6872,
3490
+ "step": 4870
3491
+ },
3492
+ {
3493
+ "epoch": 8.265932669913191,
3494
+ "grad_norm": 7.8125,
3495
+ "learning_rate": 1.9843071326986264e-07,
3496
+ "loss": 0.7416,
3497
+ "step": 4880
3498
+ },
3499
+ {
3500
+ "epoch": 8.282871056531866,
3501
+ "grad_norm": 8.3125,
3502
+ "learning_rate": 1.893667274489136e-07,
3503
+ "loss": 0.703,
3504
+ "step": 4890
3505
+ },
3506
+ {
3507
+ "epoch": 8.29980944315054,
3508
+ "grad_norm": 2.34375,
3509
+ "learning_rate": 1.8051062816799913e-07,
3510
+ "loss": 0.6915,
3511
+ "step": 4900
3512
+ },
3513
+ {
3514
+ "epoch": 8.316747829769215,
3515
+ "grad_norm": 2.109375,
3516
+ "learning_rate": 1.7186279813428518e-07,
3517
+ "loss": 0.6801,
3518
+ "step": 4910
3519
+ },
3520
+ {
3521
+ "epoch": 8.333686216387889,
3522
+ "grad_norm": 2.03125,
3523
+ "learning_rate": 1.6342361105480098e-07,
3524
+ "loss": 0.7441,
3525
+ "step": 4920
3526
+ },
3527
+ {
3528
+ "epoch": 8.350624603006564,
3529
+ "grad_norm": 2.140625,
3530
+ "learning_rate": 1.551934316202869e-07,
3531
+ "loss": 0.7246,
3532
+ "step": 4930
3533
+ },
3534
+ {
3535
+ "epoch": 8.367562989625238,
3536
+ "grad_norm": 2.140625,
3537
+ "learning_rate": 1.471726154894304e-07,
3538
+ "loss": 0.6718,
3539
+ "step": 4940
3540
+ },
3541
+ {
3542
+ "epoch": 8.384501376243913,
3543
+ "grad_norm": 1.65625,
3544
+ "learning_rate": 1.39361509273504e-07,
3545
+ "loss": 0.709,
3546
+ "step": 4950
3547
+ },
3548
+ {
3549
+ "epoch": 8.401439762862587,
3550
+ "grad_norm": 1.875,
3551
+ "learning_rate": 1.3176045052138097e-07,
3552
+ "loss": 0.7661,
3553
+ "step": 4960
3554
+ },
3555
+ {
3556
+ "epoch": 8.418378149481262,
3557
+ "grad_norm": 2.359375,
3558
+ "learning_rate": 1.2436976770495267e-07,
3559
+ "loss": 0.7727,
3560
+ "step": 4970
3561
+ },
3562
+ {
3563
+ "epoch": 8.435316536099936,
3564
+ "grad_norm": 1.703125,
3565
+ "learning_rate": 1.1718978020492988e-07,
3566
+ "loss": 0.802,
3567
+ "step": 4980
3568
+ },
3569
+ {
3570
+ "epoch": 8.45225492271861,
3571
+ "grad_norm": 1.8046875,
3572
+ "learning_rate": 1.1022079829704436e-07,
3573
+ "loss": 0.7435,
3574
+ "step": 4990
3575
+ },
3576
+ {
3577
+ "epoch": 8.469193309337285,
3578
+ "grad_norm": 1.703125,
3579
+ "learning_rate": 1.0346312313864127e-07,
3580
+ "loss": 0.7366,
3581
+ "step": 5000
3582
+ },
3583
+ {
3584
+ "epoch": 8.469193309337285,
3585
+ "eval_loss": 1.0841984748840332,
3586
+ "eval_runtime": 21.0727,
3587
+ "eval_samples_per_second": 24.914,
3588
+ "eval_steps_per_second": 24.914,
3589
+ "step": 5000
3590
+ },
3591
+ {
3592
+ "epoch": 8.48613169595596,
3593
+ "grad_norm": 2.265625,
3594
+ "learning_rate": 9.691704675565904e-08,
3595
+ "loss": 0.7348,
3596
+ "step": 5010
3597
+ },
3598
+ {
3599
+ "epoch": 8.503070082574634,
3600
+ "grad_norm": 1.953125,
3601
+ "learning_rate": 9.058285203001837e-08,
3602
+ "loss": 0.703,
3603
+ "step": 5020
3604
+ },
3605
+ {
3606
+ "epoch": 8.520008469193309,
3607
+ "grad_norm": 1.796875,
3608
+ "learning_rate": 8.446081268738971e-08,
3609
+ "loss": 0.6796,
3610
+ "step": 5030
3611
+ },
3612
+ {
3613
+ "epoch": 8.536946855811983,
3614
+ "grad_norm": 1.9140625,
3615
+ "learning_rate": 7.855119328537109e-08,
3616
+ "loss": 0.7424,
3617
+ "step": 5040
3618
+ },
3619
+ {
3620
+ "epoch": 8.553885242430658,
3621
+ "grad_norm": 1.7890625,
3622
+ "learning_rate": 7.285424920204953e-08,
3623
+ "loss": 0.7379,
3624
+ "step": 5050
3625
+ },
3626
+ {
3627
+ "epoch": 8.570823629049332,
3628
+ "grad_norm": 1.90625,
3629
+ "learning_rate": 6.737022662497095e-08,
3630
+ "loss": 0.7113,
3631
+ "step": 5060
3632
+ },
3633
+ {
3634
+ "epoch": 8.587762015668007,
3635
+ "grad_norm": 1.9140625,
3636
+ "learning_rate": 6.209936254049808e-08,
3637
+ "loss": 0.698,
3638
+ "step": 5070
3639
+ },
3640
+ {
3641
+ "epoch": 8.604700402286682,
3642
+ "grad_norm": 2.25,
3643
+ "learning_rate": 5.704188472356764e-08,
3644
+ "loss": 0.7441,
3645
+ "step": 5080
3646
+ },
3647
+ {
3648
+ "epoch": 8.621638788905356,
3649
+ "grad_norm": 2.375,
3650
+ "learning_rate": 5.219801172785255e-08,
3651
+ "loss": 0.6628,
3652
+ "step": 5090
3653
+ },
3654
+ {
3655
+ "epoch": 8.63857717552403,
3656
+ "grad_norm": 2.09375,
3657
+ "learning_rate": 4.756795287631288e-08,
3658
+ "loss": 0.7012,
3659
+ "step": 5100
3660
+ },
3661
+ {
3662
+ "epoch": 8.655515562142705,
3663
+ "grad_norm": 2.375,
3664
+ "learning_rate": 4.315190825215143e-08,
3665
+ "loss": 0.7372,
3666
+ "step": 5110
3667
+ },
3668
+ {
3669
+ "epoch": 8.67245394876138,
3670
+ "grad_norm": 1.8125,
3671
+ "learning_rate": 3.895006869016837e-08,
3672
+ "loss": 0.7353,
3673
+ "step": 5120
3674
+ },
3675
+ {
3676
+ "epoch": 8.689392335380056,
3677
+ "grad_norm": 1.6484375,
3678
+ "learning_rate": 3.496261576851345e-08,
3679
+ "loss": 0.7127,
3680
+ "step": 5130
3681
+ },
3682
+ {
3683
+ "epoch": 8.706330721998729,
3684
+ "grad_norm": 2.15625,
3685
+ "learning_rate": 3.1189721800839453e-08,
3686
+ "loss": 0.7462,
3687
+ "step": 5140
3688
+ },
3689
+ {
3690
+ "epoch": 8.723269108617405,
3691
+ "grad_norm": 2.140625,
3692
+ "learning_rate": 2.763154982885541e-08,
3693
+ "loss": 0.7486,
3694
+ "step": 5150
3695
+ },
3696
+ {
3697
+ "epoch": 8.74020749523608,
3698
+ "grad_norm": 1.9296875,
3699
+ "learning_rate": 2.4288253615282754e-08,
3700
+ "loss": 0.7136,
3701
+ "step": 5160
3702
+ },
3703
+ {
3704
+ "epoch": 8.757145881854754,
3705
+ "grad_norm": 2.046875,
3706
+ "learning_rate": 2.1159977637208452e-08,
3707
+ "loss": 0.746,
3708
+ "step": 5170
3709
+ },
3710
+ {
3711
+ "epoch": 8.774084268473429,
3712
+ "grad_norm": 1.90625,
3713
+ "learning_rate": 1.824685707984164e-08,
3714
+ "loss": 0.7379,
3715
+ "step": 5180
3716
+ },
3717
+ {
3718
+ "epoch": 8.791022655092103,
3719
+ "grad_norm": 1.9375,
3720
+ "learning_rate": 1.5549017830674416e-08,
3721
+ "loss": 0.7561,
3722
+ "step": 5190
3723
+ },
3724
+ {
3725
+ "epoch": 8.807961041710778,
3726
+ "grad_norm": 1.96875,
3727
+ "learning_rate": 1.3066576474038416e-08,
3728
+ "loss": 0.7722,
3729
+ "step": 5200
3730
+ },
3731
+ {
3732
+ "epoch": 8.824899428329452,
3733
+ "grad_norm": 2.03125,
3734
+ "learning_rate": 1.0799640286068836e-08,
3735
+ "loss": 0.7318,
3736
+ "step": 5210
3737
+ },
3738
+ {
3739
+ "epoch": 8.841837814948127,
3740
+ "grad_norm": 1.7890625,
3741
+ "learning_rate": 8.748307230067587e-09,
3742
+ "loss": 0.7358,
3743
+ "step": 5220
3744
+ },
3745
+ {
3746
+ "epoch": 8.858776201566801,
3747
+ "grad_norm": 1.7734375,
3748
+ "learning_rate": 6.912665952270581e-09,
3749
+ "loss": 0.7051,
3750
+ "step": 5230
3751
+ },
3752
+ {
3753
+ "epoch": 8.875714588185476,
3754
+ "grad_norm": 1.8203125,
3755
+ "learning_rate": 5.29279577801689e-09,
3756
+ "loss": 0.7542,
3757
+ "step": 5240
3758
+ },
3759
+ {
3760
+ "epoch": 8.89265297480415,
3761
+ "grad_norm": 2.0625,
3762
+ "learning_rate": 3.888766708319836e-09,
3763
+ "loss": 0.7354,
3764
+ "step": 5250
3765
+ },
3766
+ {
3767
+ "epoch": 8.909591361422825,
3768
+ "grad_norm": 2.1875,
3769
+ "learning_rate": 2.700639416843287e-09,
3770
+ "loss": 0.7226,
3771
+ "step": 5260
3772
+ },
3773
+ {
3774
+ "epoch": 8.9265297480415,
3775
+ "grad_norm": 2.171875,
3776
+ "learning_rate": 1.7284652472787655e-09,
3777
+ "loss": 0.7387,
3778
+ "step": 5270
3779
+ },
3780
+ {
3781
+ "epoch": 8.943468134660174,
3782
+ "grad_norm": 2.125,
3783
+ "learning_rate": 9.722862111277708e-10,
3784
+ "loss": 0.6839,
3785
+ "step": 5280
3786
+ },
3787
+ {
3788
+ "epoch": 8.960406521278848,
3789
+ "grad_norm": 2.34375,
3790
+ "learning_rate": 4.321349858843471e-10,
3791
+ "loss": 0.7071,
3792
+ "step": 5290
3793
+ },
3794
+ {
3795
+ "epoch": 8.977344907897523,
3796
+ "grad_norm": 1.9765625,
3797
+ "learning_rate": 1.080349136250991e-10,
3798
+ "loss": 0.7484,
3799
+ "step": 5300
3800
+ },
3801
+ {
3802
+ "epoch": 8.994283294516197,
3803
+ "grad_norm": 1.9375,
3804
+ "learning_rate": 0.0,
3805
+ "loss": 0.7226,
3806
+ "step": 5310
3807
+ },
3808
+ {
3809
+ "epoch": 8.994283294516197,
3810
+ "step": 5310,
3811
+ "total_flos": 5.095460800932741e+17,
3812
+ "train_loss": 0.9683849982173653,
3813
+ "train_runtime": 5676.759,
3814
+ "train_samples_per_second": 7.488,
3815
+ "train_steps_per_second": 0.935
3816
+ }
3817
+ ],
3818
+ "logging_steps": 10,
3819
+ "max_steps": 5310,
3820
+ "num_input_tokens_seen": 0,
3821
+ "num_train_epochs": 9,
3822
+ "save_steps": 0,
3823
+ "stateful_callbacks": {
3824
+ "TrainerControl": {
3825
+ "args": {
3826
+ "should_epoch_stop": false,
3827
+ "should_evaluate": false,
3828
+ "should_log": false,
3829
+ "should_save": true,
3830
+ "should_training_stop": true
3831
+ },
3832
+ "attributes": {}
3833
+ }
3834
+ },
3835
+ "total_flos": 5.095460800932741e+17,
3836
+ "train_batch_size": 1,
3837
+ "trial_name": null,
3838
+ "trial_params": null
3839
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe6f6e1a55b6ce6e9636cb2316a96482aeec5c5fc5be4262f061ad26b88ececb
3
+ size 5304
training_eval_loss.png ADDED
training_loss.png ADDED